© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37168
    Prev
    Next
    INDEX
    Explanations

    Kylie, Malala, Haley, Wynonna

    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±Ĥå±Ĥ
    -0.09
    ifice
    -0.09
    æ¶ŀ
    -0.08
    åIJĪ并
    -0.08
    евой
    -0.08
     mel
    -0.08
    æīĴ
    -0.07
     peach
    -0.07
    æ³®
    -0.07
    èıĬ
    -0.07
    POSITIVE LOGITS
    ç£ķ
    0.11
    趸
    0.10
    à¸Ľà¸ı
    0.09
    çł£
    0.09
    _soc
    0.09
    .sprites
    0.09
    山水
    0.09
    кан
    0.09
    /Grid
    0.09
    гÑĢан
    0.09
    Activations Density 0.002%

    No Known Activations