© 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. 31234
    Prev
    Next
    INDEX
    Explanations

    family relationships

    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
    ç»ıæµİ社ä¼ļ
    -0.10
    ignon
    -0.09
    åı©
    -0.09
    LAT
    -0.09
    åĸīåĴĻ
    -0.09
    åIJİæľŁ
    -0.08
    人人éĥ½
    -0.08
    lat
    -0.08
    åĽ´è§Ĥ
    -0.08
    çļĦæĿĥåĪ©
    -0.08
    POSITIVE LOGITS
    esc
    0.09
    æĢĽ
    0.09
    utter
    0.08
    çİĭèĢħ
    0.08
    éĿ¢åIJij
    0.08
     moll
    0.08
    ourt
    0.08
    esk
    0.08
    çIJĨçĶ±
    0.08
    htm
    0.08
    Activations Density 0.021%

    No Known Activations