© 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. 35082
    Prev
    Next
    INDEX
    Explanations

    hair and nail conditions

    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
    å¤Ķ
    -0.09
    éĢĤ
    -0.09
    èĢĹ
    -0.09
     Spare
    -0.08
    æ»´
    -0.08
    MOTE
    -0.08
    bras
    -0.08
    ä¸įåIJĮæĦı
    -0.08
     Banc
    -0.08
    elder
    -0.08
    POSITIVE LOGITS
    iese
    0.09
    æĢĿç»´æĸ¹å¼ı
    0.09
    æ¯ĽåŃĶ
    0.09
    çİĭåħĪçĶŁ
    0.09
    ansi
    0.09
    ench
    0.08
    ä¸Ģæł¹
    0.08
    æ±Ĺ
    0.08
    åºĬä½į
    0.08
    çĩİ
    0.08
    Activations Density 0.136%

    No Known Activations