© 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. 20-TRANSCODER-HP
    7. 129372
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    輩
    -0.29
    ium
    -0.26
    |RF
    -0.25
    egrate
    -0.25
    ôme
    -0.24
    rior
    -0.24
    clid
    -0.24
    åĵĻ
    -0.24
    InChildren
    -0.24
    <Unit
    -0.24
    POSITIVE LOGITS
    çľĭå¾Ĺ
    0.30
    è¿Ļåı¥è¯Ŀ
    0.27
    è¿Ļæĺ¯ä¸Ģ个
    0.26
    ä¸Ģ个æĸ°çļĦ
    0.25
    èĿĮ
    0.25
     Exactly
    0.24
     hoÃłn
    0.24
    hor
    0.24
    è¿Ļ段
    0.24
     acknowledges
    0.24
    Activations Density 27.862%

    No Known Activations