© 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. 129680
    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
    話
    -0.24
    WARD
    -0.24
    anical
    -0.24
    usions
    -0.24
    è¯Ŀ
    -0.23
    ucene
    -0.23
    åł±
    -0.23
    微信åı·
    -0.23
     result
    -0.22
    _CN
    -0.22
    POSITIVE LOGITS
    åħ¨å®¶
    0.25
    å¸
    0.24
     applyMiddleware
    0.23
    Gain
    0.23
    lah
    0.23
    åıĹçĽĬ
    0.23
    ,...↵
    0.22
     EXEC
    0.22
     polled
    0.22
    表æ¼Ķ
    0.21
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.