© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40158
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬĬ她
    -0.31
    uada
    -0.28
    å®ŀçĶ¨
    -0.28
    æıIJåĩºçļĦ
    -0.27
    缴æİ¥
    -0.26
    æ¶Ĥ
    -0.26
    HA
    -0.26
     classical
    -0.25
    ras
    -0.25
    OUN
    -0.25
    POSITIVE LOGITS
     findBy
    0.28
    /Edit
    0.26
     ----------------------------------------------------------------------------------------------------------------
    0.25
     ################################################################
    0.24
     a
    0.24
    FindObject
    0.24
    InTheDocument
    0.24
    æĶ¾è¿ĩ
    0.24
     dép
    0.24
    achu
    0.23
    Activations Density 0.040%

    No Known Activations