© 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. 39018
    Prev
    Next
    INDEX
    Explanations

    B

    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
    LEM
    -0.36
     popcorn
    -0.31
    çŨ
    -0.31
     Wash
    -0.29
     Bracket
    -0.26
    VID
    -0.26
     Operator
    -0.26
     Loud
    -0.25
    -Language
    -0.25
     Vand
    -0.25
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.29
    亲
    0.29
    éĩĩçĶ¨
    0.28
     çekil
    0.27
    ¸
    0.26
    è¿Ļ两ç§į
    0.26
    親
    0.26
    èĩ£
    0.25
    çļĦä¸Ģ
    0.24
     deciding
    0.24
    Activations Density 0.019%

    No Known Activations