© 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. 21983
    Prev
    Next
    INDEX
    Explanations

    free

    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
    Negative Logits
    aid
    -0.28
    大æłij
    -0.26
     contributes
    -0.26
     Flames
    -0.26
    OTH
    -0.25
    åĺ²ç¬ij
    -0.24
     duel
    -0.24
    {id
    -0.24
     contributed
    -0.24
    atoes
    -0.23
    POSITIVE LOGITS
    åį°
    0.28
    ripp
    0.28
    ä¸Ńç¾İ
    0.26
    cac
    0.26
    urred
    0.26
    ãĥģãĥ³
    0.26
    -middle
    0.26
    ä¸Ńæ¯Ĵ
    0.25
    ç¨İè´¹
    0.25
    printStats
    0.24
    Activations Density 0.048%

    No Known Activations