© 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. 87468
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    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
    attr
    -0.26
     relent
    -0.26
    æĸ¹è¨Ģ
    -0.26
     homosexuality
    -0.25
     Attr
    -0.24
    removeAttr
    -0.24
    inki
    -0.24
    parse
    -0.24
    float
    -0.24
    è½²
    -0.24
    POSITIVE LOGITS
     probably
    0.28
    ấy
    0.27
    /report
    0.26
    arium
    0.26
    çī¹
    0.24
    ูล
    0.24
     Probably
    0.23
    Bloc
    0.23
    éĥ½èĥ½å¤Ł
    0.23
    itized
    0.23
    Activations Density 0.016%

    No Known Activations