© 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. 87946
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    aspect
    -0.27
     aspect
    -0.26
    оваÑĤÑĮ
    -0.26
    æĸ¹éĿ¢çļĦ
    -0.25
     pal
    -0.24
    assen
    -0.24
     Cad
    -0.24
    ò
    -0.24
     Cont
    -0.24
    pal
    -0.24
    POSITIVE LOGITS
    ä¸¤åĽ½
    0.30
    InteractionEnabled
    0.27
     impress
    0.25
    perial
    0.25
     nisi
    0.24
    æİĴ
    0.24
    UrlParser
    0.24
    æĿľ
    0.24
    äºĴéĢļ
    0.24
     {:?}",
    0.23
    Activations Density 0.009%

    No Known Activations