© 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. 33-TRANSCODER-HP
    7. 52840
    Prev
    Next
    INDEX
    Explanations

    biomedical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gan
    -0.30
     em
    -0.29
     the
    -0.28
    鸣
    -0.27
     covers
    -0.26
     tens
    -0.26
     dyn
    -0.25
     keep
    -0.25
     cover
    -0.25
     Keep
    -0.24
    POSITIVE LOGITS
    eria
    0.30
    çĹħæ¯ĴæĦŁæŁĵ
    0.27
    itta
    0.27
    对æĪij
    0.27
    å·´åŁº
    0.27
    ernet
    0.27
    LError
    0.26
    è¿Ļ个åIJįåŃĹ
    0.26
     )->
    0.26
    è¾ĺ
    0.25
    Activations Density 0.005%

    No Known Activations