© 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. 48681
    Prev
    Next
    INDEX
    Explanations

    look in the mirror

    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
    åŃĹä½ĵ
    -0.09
    æ¸ĹéĢı
    -0.09
    åIJĦèĩª
    -0.09
    åIJĦèĩªçļĦ
    -0.09
    åı·
    -0.08
     onRequest
    -0.08
    建ç«ĭåģ¥åħ¨
    -0.08
    çį»
    -0.08
    ç¾Ĭ
    -0.08
    иÑĤа
    -0.08
    POSITIVE LOGITS
     selfie
    0.13
    éķľåŃIJ
    0.13
    èĩªå·±
    0.12
    èĩªå·±çļĦ
    0.11
    _self
    0.11
    èĩªæĪij
    0.11
    reflection
    0.11
    .self
    0.11
    èľĥ
    0.10
    对èĩªå·±çļĦ
    0.10
    Activations Density 0.036%

    No Known Activations