© 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. 87756
    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
    西åįĹ
    -0.30
    西éĥ¨
    -0.28
     southwestern
    -0.26
    idian
    -0.26
    onaut
    -0.25
    ½æķ°
    -0.25
    Ùħت
    -0.25
    _armor
    -0.24
    è§Ĩ为
    -0.24
    åįĹæĸ¹
    -0.24
    POSITIVE LOGITS
    rait
    0.28
     remembers
    0.26
    ute
    0.26
    éĤ£åıª
    0.26
    *******/↵↵
    0.24
    èĦ¸
    0.24
    erving
    0.24
    äºijéĽĨ
    0.24
    rising
    0.24
     uv
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.