© 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. 142677
    Prev
    Next
    INDEX
    Explanations

    retrieve

    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
    Negative Logits
    "go
    -0.28
    entic
    -0.27
    uld
    -0.26
    idden
    -0.26
    edelta
    -0.26
    .getBounds
    -0.25
    entes
    -0.24
    è¿ĺä¸įå¤Ł
    -0.24
    ault
    -0.24
    /she
    -0.23
    POSITIVE LOGITS
    _ALIAS
    0.27
    oop
    0.26
    (^
    0.25
    충
    0.24
    `),↵
    0.24
    Alias
    0.23
    åĨ¶çĤ¼
    0.23
     PAL
    0.23
    Past
    0.23
    Interior
    0.23
    Activations Density 1.975%

    No Known Activations