© 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. 55615
    Prev
    Next
    INDEX
    Explanations

    one another

    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
     Prob
    -0.09
    æ¸ħ
    -0.09
    æĬĸ
    -0.08
    Prob
    -0.08
     unordered
    -0.08
    éĶ»
    -0.08
    coles
    -0.07
    Adventure
    -0.07
    raj
    -0.07
    æ¸
    -0.07
    POSITIVE LOGITS
     kind
    0.11
    ç±»åŀĭçļĦ
    0.10
     SPELL
    0.10
    èIJ¥
    0.10
    czÄĻ
    0.10
     KIND
    0.09
    å®ıä¼Ł
    0.09
    kind
    0.09
    çݺ
    0.09
    ä½ļ
    0.09
    Activations Density 0.058%

    No Known Activations