© 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. 1038
    Prev
    Next
    INDEX
    Explanations

    amazon fire tv, kindle fire tablet

    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
    å¸Ń
    -0.10
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    åŁķ
    -0.09
    æ±Ľ
    -0.09
    éĩįåŀĭ
    -0.08
    joined
    -0.08
    溷
    -0.08
    Ho
    -0.08
    çĦĻ
    -0.08
    _GRANTED
    -0.08
    POSITIVE LOGITS
    èµı
    0.09
    èķī
    0.09
    ä¹łä¿Ĺ
    0.08
    ánt
    0.08
    oce
    0.08
    cott
    0.08
    宽带
    0.08
     Fargo
    0.08
    Metro
    0.08
    éħĭ
    0.08
    Activations Density 0.003%

    No Known Activations