© 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. 62900
    Prev
    Next
    INDEX
    Explanations

    Long, complex sentences

    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
    hof
    -0.28
     clar
    -0.27
    è¿Ļ个åIJįåŃĹ
    -0.26
    ä¸ºæł¸å¿ĥ
    -0.26
    çļĦ帮åĬ©
    -0.25
    ymbols
    -0.24
    /Gate
    -0.24
    樾
    -0.24
     Goldman
    -0.24
    èĦ«
    -0.23
    POSITIVE LOGITS
    irts
    0.27
    rens
    0.26
    /archive
    0.25
    ÑīиÑĤ
    0.24
     Shame
    0.24
    PEnd
    0.24
    åģ¾
    0.24
     Attachment
    0.23
    andles
    0.23
    leaning
    0.23
    Activations Density 25.135%

    No Known Activations