© 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. 39659
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åIJĮæŶ
    -0.31
    次
    -0.26
    irement
    -0.26
     MotionEvent
    -0.26
    ired
    -0.26
     Friendly
    -0.25
    rible
    -0.25
    涨
    -0.25
    ä¸ĭéĿ¢
    -0.24
     Apart
    -0.24
    POSITIVE LOGITS
     inconsist
    0.26
     liber
    0.26
    åľ¨çº¿åĴ¨è¯¢
    0.26
    å¼ķæĵİ
    0.25
     molecular
    0.25
    ãģĹãģ¾
    0.25
     shores
    0.25
     liberty
    0.24
    èŀŃ
    0.24
    è¯ĥ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.