© 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. 22174
    Prev
    Next
    INDEX
    Explanations

    Western

    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
    容
    -0.31
    <html
    -0.27
    çĵ·
    -0.26
    andler
    -0.26
    论
    -0.26
    è§Ħç¨ĭ
    -0.26
    cline
    -0.25
    Prototype
    -0.25
    误差
    -0.25
    çĬ¯è§Ħ
    -0.25
    POSITIVE LOGITS
    atto
    0.31
    è§ģè¿ĩ
    0.27
     Indies
    0.26
    æ·±æĥħ
    0.25
    æĮ½
    0.24
     vidé
    0.24
    ieves
    0.24
    毫ä¸įçĬ¹è±«
    0.23
    .DropDown
    0.23
     grown
    0.23
    Activations Density 0.001%

    No Known Activations