© 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. 24-TRANSCODER-HP
    7. 149460
    Prev
    Next
    INDEX
    Explanations

    psychologist

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lat
    -0.27
    EVER
    -0.25
    éĻĭ
    -0.24
     ÑĤоÑĩно
    -0.24
     measurement
    -0.24
    TRS
    -0.24
    While
    -0.24
    lat
    -0.23
    INI
    -0.23
    æµĭéĩı
    -0.23
    POSITIVE LOGITS
    -ended
    0.27
    åŃIJå¼Ł
    0.25
     wives
    0.23
    loff
    0.23
    agal
    0.23
    å¸ĮæľĽå¤§å®¶
    0.23
    iec
    0.23
    èĥ½å¾ĹåĪ°
    0.23
    -master
    0.23
    èĺħ
    0.23
    Activations Density 0.393%

    No Known Activations