© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21087
    Prev
    Next
    INDEX
    Explanations

    skeletal muscle and anatomy

    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
    umption
    -0.09
    byn
    -0.09
    lander
    -0.09
    èľ©
    -0.08
    ussy
    -0.08
     Noon
    -0.08
    é£Ł
    -0.08
    èĮ§
    -0.08
    æģ¶å¿ĥ
    -0.08
    omens
    -0.08
    POSITIVE LOGITS
    cial
    0.10
    åŀ¢
    0.09
    对æłĩ
    0.09
    éĩįæķ´
    0.09
    lke
    0.08
    mw
    0.08
    ized
    0.08
     давно
    0.08
    é«ħ
    0.08
    lv
    0.08
    Activations Density 0.006%

    No Known Activations