© 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. 22509
    Prev
    Next
    INDEX
    Explanations

    acupuncture potencies

    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
    _IMPLEMENT
    -0.09
    mpr
    -0.09
    éĽħ
    -0.09
    æĭ³å¤´
    -0.09
    åģľä¸ĭæĿ¥
    -0.09
    globals
    -0.09
    unbind
    -0.08
     رس
    -0.08
     wishes
    -0.08
    )(__
    -0.08
    POSITIVE LOGITS
    æķħ宫
    0.10
    æ¸ħæľĿ
    0.10
    æī¿
    0.10
    ç²¹
    0.10
    çİĭåºľ
    0.09
    æ²Īéĺ³
    0.09
    æī¿å¾·
    0.09
    女è£ħ
    0.08
    ä¼ı
    0.08
    åİĨåı²æĸ°
    0.08
    Activations Density 0.033%

    No Known Activations