© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142320
    Prev
    Next
    INDEX
    Explanations

    necessities

    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
    åįĬå²Ľ
    -0.27
     crack
    -0.26
     cầm
    -0.23
     radioactive
    -0.23
    sch
    -0.23
    oste
    -0.23
    bud
    -0.23
     jane
    -0.23
     reproduction
    -0.23
    dent
    -0.23
    POSITIVE LOGITS
     marvel
    0.28
    顺便
    0.27
    itionally
    0.27
    ниÑĨ
    0.26
    Ã¼ÄŁ
    0.26
    ÑĤки
    0.25
    幸ç¦ı
    0.24
    estic
    0.23
    usic
    0.23
    éĻ·éĺ±
    0.23
    Activations Density 15.997%

    No Known Activations