© 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. 5740
    Prev
    Next
    INDEX
    Explanations

    exclamations of excitement

    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
    bane
    -0.10
    rage
    -0.10
    ваÑĤ
    -0.09
     vag
    -0.09
    age
    -0.09
    OfDay
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    OND
    -0.08
    çĿļ
    -0.08
    累累
    -0.08
    POSITIVE LOGITS
    å·§åIJĪ
    0.09
    -columns
    0.09
    ully
    0.09
    åĿ¨
    0.09
    fully
    0.08
    ç»ĵæŀľ
    0.08
    享çĶ¨
    0.08
    ouden
    0.08
    kening
    0.08
    UTH
    0.08
    Activations Density 0.003%

    No Known Activations