© 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. 98794
    Prev
    Next
    INDEX
    Explanations

    feedback

    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
    èĤī
    -0.28
     lending
    -0.25
    ç»ĪçĤ¹
    -0.25
    put
    -0.24
    è¯ĨåĪ«
    -0.24
    .masks
    -0.23
    æĻ¶
    -0.23
    erd
    -0.23
    ürlich
    -0.23
     Bounds
    -0.23
    POSITIVE LOGITS
     wish
    0.28
     Cougar
    0.26
    æľīä»·åĢ¼çļĦ
    0.25
    зв
    0.25
    itia
    0.25
     Cá
    0.25
    ulta
    0.25
     sunday
    0.23
    ç¦Ģ
    0.23
     Competitive
    0.23
    Activations Density 0.037%

    No Known Activations