© 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. 111974
    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
    ULATE
    -0.26
    ç»ĵæŀĦæĢ§
    -0.26
    è´°
    -0.25
    .creator
    -0.24
    .setBorder
    -0.24
     bootstrap
    -0.23
     borderBottom
    -0.23
    .syntax
    -0.23
     Dur
    -0.23
     Pasta
    -0.23
    POSITIVE LOGITS
    ä¸į失
    0.27
    mentation
    0.26
    mented
    0.25
    æĹłéļľç¢į
    0.24
    éĥ¾
    0.24
    ments
    0.24
    ÑĤел
    0.24
     omn
    0.24
    .om
    0.23
    gerald
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.