© 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. 12-TRANSCODER-HP
    7. 22222
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÈĽi
    -0.27
    .currentTarget
    -0.26
    ä¼ł
    -0.26
     chemical
    -0.26
    ointed
    -0.26
    @qq
    -0.25
     calor
    -0.25
    ä»Ĭ
    -0.24
    è·Łä»ĸ
    -0.24
    äºĶè¡Į
    -0.24
    POSITIVE LOGITS
    utz
    0.28
    æ¡ĥ
    0.27
    èĻİ
    0.27
    alto
    0.27
    èµĦ
    0.26
    etz
    0.26
    worth
    0.26
    forecast
    0.24
    ç¨ļ
    0.24
    edia
    0.24
    Activations Density 0.002%

    No Known Activations