© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9596
    Prev
    Next
    INDEX
    Explanations

    sport and games

    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
    Void
    -0.09
    åĬ¿
    -0.08
    iso
    -0.08
    ordo
    -0.08
    inde
    -0.08
    MB
    -0.08
    è¡·
    -0.08
    azzo
    -0.08
    ords
    -0.08
    æķĪåºĶ
    -0.08
    POSITIVE LOGITS
    å¿Ĺ强
    0.11
    ä¸Ģæīĭ
    0.10
    uckle
    0.10
    unken
    0.10
    裸
    0.10
    åľ°éģĵ
    0.09
    ston
    0.09
    _OPTS
    0.09
    å¢ŀåĬłåĢ¼
    0.09
     naked
    0.09
    Activations Density 0.090%

    No Known Activations