© 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. 97977
    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
    иÑĨе
    -0.25
    emean
    -0.24
    ilyn
    -0.24
    auses
    -0.23
    adem
    -0.23
    quÃŃ
    -0.23
     Cin
    -0.23
    hra
    -0.23
    uchos
    -0.23
    acent
    -0.22
    POSITIVE LOGITS
    wo
    0.24
    æ±ł
    0.24
    marks
    0.24
    ï¼ł
    0.24
    åIJIJ
    0.24
    _marks
    0.23
    åħīæºIJ
    0.23
    ter
    0.23
     belong
    0.22
     fort
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.