© 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. 106930
    Prev
    Next
    INDEX
    Explanations

    Incomplete 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
    åħħ满
    -0.31
    æĬļ
    -0.27
     Joi
    -0.26
    pé
    -0.26
    èĬ®
    -0.25
    çŃ¾ä¸ĭ
    -0.24
    ispens
    -0.24
    _Copy
    -0.24
    nop
    -0.24
    ãģ¤ãģĭ
    -0.24
    POSITIVE LOGITS
    åIJijåīį
    0.27
     flat
    0.26
     водо
    0.24
     prox
    0.24
    æĿ¥çĶµ
    0.23
     ado
    0.23
     Powell
    0.23
    ä¼łåĩº
    0.23
     remote
    0.23
     counties
    0.23
    Activations Density 0.094%

    No Known Activations