© 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. 22214
    Prev
    Next
    INDEX
    Explanations

    physical abnormalities/irregularities

    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
    èĬĤ
    -0.31
     settling
    -0.30
     settles
    -0.30
    WEB
    -0.28
     settle
    -0.27
    ç»Ħéķ¿
    -0.26
     componente
    -0.26
     brief
    -0.26
     forgive
    -0.25
    纸
    -0.25
    POSITIVE LOGITS
    åıį
    0.28
    éĢĨ转
    0.26
    åıį转
    0.25
    orientation
    0.24
    arity
    0.24
    .asm
    0.24
    dbuf
    0.24
     Sandwich
    0.24
    èĮĥ
    0.24
    yped
    0.24
    Activations Density 0.003%

    No Known Activations