© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3751
    Prev
    Next
    INDEX
    Explanations

    wallpaper, saver, Wifi, panda, headlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umph
    -0.09
    AxisSize
    -0.09
    Ìģ
    -0.09
     manufactures
    -0.08
    lut
    -0.08
    estro
    -0.08
    wig
    -0.08
    gary
    -0.08
    ildo
    -0.08
    ighthouse
    -0.08
    POSITIVE LOGITS
    ä¸ĭè°ĥ
    0.10
    è³¢
    0.09
    ä¸Ģå¼ł
    0.09
    паÑĢ
    0.09
    å«īå¦Ĵ
    0.08
    åŁĴ
    0.08
    odate
    0.08
    大åħ¨
    0.08
    èĮ¬
    0.08
    olk
    0.08
    Activations Density 0.003%

    No Known Activations