© 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. 24056
    Prev
    Next
    INDEX
    Explanations

    programming/technical processes

    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
    idUser
    -0.28
    <decltype
    -0.26
    ades
    -0.25
    åĵķ
    -0.24
    绽
    -0.24
     Scholarship
    -0.24
     Evo
    -0.24
    asin
    -0.24
    èī²è°ĥ
    -0.24
    ieme
    -0.24
    POSITIVE LOGITS
    稿
    0.27
    èĥĮåIJİ
    0.27
    天èĬ±
    0.26
    赤
    0.26
    ialis
    0.26
    tha
    0.25
    èĩ³æѤ
    0.25
    wear
    0.25
    èĥĮä¸Ĭ
    0.25
     trif
    0.24
    Activations Density 0.000%

    No Known Activations