© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112352
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Bry
    -0.27
    èĨ¨èĥĢ
    -0.26
    足
    -0.26
    亲
    -0.25
    noinspection
    -0.25
    太大
    -0.23
    ÙĬض
    -0.23
    (/^
    -0.23
    å¾·å·ŀ
    -0.23
    åŃij
    -0.23
    POSITIVE LOGITS
    è¾¾
    0.27
    éĢļæĬ¥
    0.26
    annie
    0.25
    rine
    0.25
     thous
    0.24
     WOM
    0.24
     unre
    0.24
    è¾¾æłĩ
    0.23
    XM
    0.23
     kh
    0.23
    Activations Density 0.062%

    No Known Activations

    This feature has no known activations.