© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    statistical methods and theory

    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
    峪
    -0.09
    CloseOperation
    -0.09
    稷
    -0.08
    Ø·Ùģ
    -0.08
    éĢļåħ³
    -0.08
    æľįåĬ¡ä½ĵç³»
    -0.08
    éĥĦ
    -0.08
    çļĦäºĭå®ŀ
    -0.08
    dump
    -0.08
    åĩºåħ¥
    -0.08
    POSITIVE LOGITS
    稳åģ¥
    0.10
    wald
    0.09
    ivot
    0.08
    ror
    0.08
     practitioner
    0.08
    ÃĤN
    0.08
    ELSE
    0.08
    PROC
    0.08
     Coch
    0.08
    iid
    0.08
    Activations Density 0.529%

    No Known Activations