© 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. 22218
    Prev
    Next
    INDEX
    Explanations

    technical and scientific documents

    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
    å°±çŁ¥éģĵ
    -0.32
    $self
    -0.26
    è¯ķè¯ķ
    -0.25
    æīįçŁ¥éģĵ
    -0.24
    MOVE
    -0.24
    ATURE
    -0.24
    ä¸ĭåİ»
    -0.23
    æ°Ĺãģ¥
    -0.23
    èĵĵ
    -0.23
     setattr
    -0.23
    POSITIVE LOGITS
    æľīä¸Ģä½į
    0.28
    rá
    0.25
    追æ±Ĥ
    0.25
     occupation
    0.25
    æ³ķå¾ĭ
    0.24
    à¤ĵ
    0.24
     maximum
    0.24
    ä¿ĥè¿Ľ
    0.24
     Char
    0.23
    横
    0.23
    Activations Density 0.004%

    No Known Activations