© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23880
    Prev
    Next
    INDEX
    Explanations

    Code and text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æııåĨĻ
    -0.29
     param
    -0.28
    æĮ£éĴ±
    -0.27
     pund
    -0.27
    åŃĺéĩı
    -0.26
     straight
    -0.26
    ä¸įä¸ĭ
    -0.25
     opponent
    -0.25
     Param
    -0.25
     prof
    -0.25
    POSITIVE LOGITS
    éĥ½åľ¨
    0.28
    ^K
    0.28
    èŀį
    0.26
    acci
    0.26
     lodge
    0.25
    ãģĹãģŁãĤĤãģ®
    0.25
    离éĢĢä¼ij
    0.25
    irit
    0.24
    æ´Ĺå¹²åĩĢ
    0.24
    THR
    0.24
    Activations Density 0.000%

    No Known Activations