© 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. 111862
    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
    visualization
    -0.25
     respective
    -0.25
     std
    -0.24
     port
    -0.24
    ĥģ
    -0.24
    è·³
    -0.24
    .openg
    -0.23
     second
    -0.23
    ighth
    -0.23
     standard
    -0.23
    POSITIVE LOGITS
    Atoms
    0.29
    imson
    0.25
    说å®Į
    0.25
     Downs
    0.24
    enal
    0.24
    å¤ļä¹Ī
    0.23
     sacked
    0.23
    egal
    0.23
    çİ©ç¬ij
    0.23
    ulerAngles
    0.22
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.