© 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. 111725
    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
    --*/↵
    -0.28
    --)↵
    -0.28
    ')");↵
    -0.25
    Het
    -0.25
    remaining
    -0.25
    imeter
    -0.25
    Forms
    -0.24
     dipped
    -0.24
    imeters
    -0.24
    Remaining
    -0.24
    POSITIVE LOGITS
    æ´»åĬ¨ä¸Ń
    0.27
    éķĴ
    0.26
    åŃĶ
    0.26
    ive
    0.25
    åı£ä¸Ń
    0.25
    .ua
    0.25
    nds
    0.25
    ında
    0.24
    [w
    0.24
     w
    0.24
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.