© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8680
    Prev
    Next
    INDEX
    Explanations

    beat or rhythm

    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
    å½±
    -0.10
    IFO
    -0.10
    群ä½ĵ
    -0.09
    èľĥ
    -0.09
    æ³³
    -0.09
    转åŀĭåıijå±ķ
    -0.09
    IRA
    -0.09
    ê¸ī
    -0.08
    ģı
    -0.08
    ë£Į
    -0.08
    POSITIVE LOGITS
    èĬĤå¥ı
    0.15
     rhythm
    0.12
     beat
    0.11
     nhá»ĭ
    0.10
     beats
    0.10
     rhythms
    0.10
    åĤ¬
    0.09
    欹
    0.09
    é¡¹çĽ®ç»ıçIJĨ
    0.08
     rhyth
    0.08
    Activations Density 0.039%

    No Known Activations