© 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. 22-TRANSCODER-HP
    7. 130955
    Prev
    Next
    INDEX
    Explanations

    Organizations and place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ninety
    -0.25
    EFR
    -0.25
    Ä°Åŀ
    -0.25
    è¡¥
    -0.24
    WISE
    -0.24
    åļ¼
    -0.23
    è¾ĸåĮº
    -0.23
    äºĶåįĥ
    -0.23
     eighteen
    -0.22
    被迫
    -0.22
    POSITIVE LOGITS
    datum
    0.26
    ogram
    0.25
    esto
    0.24
    ponde
    0.23
    è¨Ģ
    0.23
    0.23
    é¢ł
    0.23
    #ifndef
    0.23
    atoon
    0.23
    inson
    0.23
    Activations Density 0.077%

    No Known Activations