© 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. 98801
    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
    qid
    -0.28
    GetObject
    -0.25
     ?>>↵
    -0.25
    eid
    -0.25
    :NS
    -0.24
    ï¼Ł↵
    -0.23
    )+↵
    -0.23
    ï¼Ľ↵
    -0.23
     ldc
    -0.23
     */↵
    -0.23
    POSITIVE LOGITS
    ernaut
    0.31
    oren
    0.27
     funct
    0.26
    饱满
    0.25
    趣
    0.25
    svm
    0.25
    åµļ
    0.25
     placements
    0.24
    emean
    0.23
     ounce
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.