© 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. 27-TRANSCODER-HP
    7. 7998
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .dateFormat
    -0.30
    æĹ¥åīį
    -0.28
    å¹´åīį
    -0.28
    getDate
    -0.28
    DateFormat
    -0.28
     formatDate
    -0.28
    æĹ¥æľŁ
    -0.27
    Date
    -0.27
    :date
    -0.26
    =date
    -0.26
    POSITIVE LOGITS
    hest
    0.30
    Experiment
    0.29
    *-
    0.28
     Experiment
    0.27
    Plate
    0.27
     @(
    0.26
    ç¢į
    0.26
    _plate
    0.25
    ä½İ端
    0.25
    è§Ħ模以ä¸Ĭ
    0.25
    Activations Density 0.008%

    No Known Activations