© 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. 23937
    Prev
    Next
    INDEX
    Explanations

    bite

    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
    Integration
    -0.26
     Integration
    -0.26
     integrates
    -0.25
    issy
    -0.24
     Integr
    -0.24
    èĩªåľ¨
    -0.24
    ий
    -0.23
    hi
    -0.23
    æİ¥åħ¥
    -0.23
     reprodu
    -0.23
    POSITIVE LOGITS
    ilateral
    0.28
    eva
    0.27
    NZ
    0.27
    éĢı
    0.26
    .blocks
    0.25
     Thatcher
    0.25
     Attribution
    0.25
     sharpen
    0.25
    (^)(
    0.25
    ä¹ħ
    0.25
    Activations Density 0.002%

    No Known Activations