© 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. 31720
    Prev
    Next
    INDEX
    Explanations

    electronic musical instruments

    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
    绶
    -0.10
    帷
    -0.09
    åĶł
    -0.09
    æ»
    -0.09
    .detect
    -0.09
    åľ°æ®µ
    -0.08
    èĩªä¸»åĵģçīĮ
    -0.08
    é¦ĸå¸Ń
    -0.08
     Authority
    -0.08
    帽åŃIJ
    -0.08
    POSITIVE LOGITS
    æ¡£
    0.10
    å¢Ł
    0.10
    è¯ī
    0.10
    é¼ł
    0.09
     Welch
    0.09
    åħįéĻ¤
    0.08
    ива
    0.08
    halb
    0.08
     corr
    0.08
     Lar
    0.08
    Activations Density 0.076%

    No Known Activations