© 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. 39771
    Prev
    Next
    INDEX
    Explanations

    ped

    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
    ä¿ĿéĻ©
    -0.28
    ä¸Ģ举
    -0.26
    å°Ŀ
    -0.26
     Binder
    -0.25
     ens
    -0.24
    ç§ijåѦ
    -0.24
    çĻ¾ä¸ĩ
    -0.24
    BIND
    -0.23
    稳å®ļ
    -0.23
    ä¸ĢéĿ¢
    -0.23
    POSITIVE LOGITS
    ive
    0.45
    icient
    0.38
    ulent
    0.36
    acent
    0.36
    ematic
    0.35
    irl
    0.34
    gether
    0.34
    ortion
    0.33
    edge
    0.33
    odore
    0.33
    Activations Density 0.013%

    No Known Activations