© 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. 31-TRANSCODER-HP
    7. 19595
    Prev
    Next
    INDEX
    Explanations

    Start of papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lex
    -0.28
     lex
    -0.27
    第ä¸Ģéĥ¨
    -0.27
    æ³ķå®Ŀ
    -0.26
    _lex
    -0.26
     Tomorrow
    -0.26
     px
    -0.25
    aign
    -0.25
    Lex
    -0.24
    _under
    -0.24
    POSITIVE LOGITS
     Situation
    0.26
    Scaler
    0.26
    Propagation
    0.26
    akens
    0.26
    åģ¥åº·
    0.25
    enumerate
    0.25
    STRACT
    0.25
    indrical
    0.24
     Paran
    0.24
    身ä½ĵ
    0.24
    Activations Density 0.022%

    No Known Activations