© 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. 130171
    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
    /sites
    -0.26
    Ord
    -0.26
    ordin
    -0.25
     Ordinary
    -0.25
    ourd
    -0.25
    æĻ®éĢļ
    -0.25
    ember
    -0.24
    çĹĺ
    -0.23
    idget
    -0.23
    <Option
    -0.23
    POSITIVE LOGITS
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.26
     ox
    0.25
    OOSE
    0.24
     Sponsored
    0.24
    OLUTE
    0.24
    imes
    0.24
    主任
    0.23
     growth
    0.23
    滥
    0.23
    anmar
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.