© 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. 7441
    Prev
    Next
    INDEX
    Explanations

    names like gretchen, garrett, reese

    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
    ì§Ŀ
    -0.10
    иÑĢование
    -0.09
    дÑĢ
    -0.09
    æŁ¬
    -0.09
    íĥĿ
    -0.09
    รà¸Ńย
    -0.09
    åĿĢ
    -0.09
    rices
    -0.09
    ä½ķå¿ħ
    -0.09
    éĿ
    -0.08
    POSITIVE LOGITS
    踪
    0.10
    èķĪ
    0.09
    ably
    0.09
    æ®·
    0.09
    oken
    0.09
    æį®ç»Łè®¡
    0.08
    arget
    0.08
    opolitan
    0.08
    cke
    0.08
    ogan
    0.08
    Activations Density 0.003%

    No Known Activations