© 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. 48400
    Prev
    Next
    INDEX
    Explanations

    gene encoding

    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
    cue
    -0.09
    dan
    -0.09
    äºĨä¸Ģä¸ĭ
    -0.09
    ä¸Ģæŀ¶
    -0.08
    éĽĨç»ĵ
    -0.08
    åħŃåIJĪ
    -0.08
    æĥŁ
    -0.08
    cot
    -0.08
    udy
    -0.08
     CMS
    -0.08
    POSITIVE LOGITS
    wagon
    0.10
    马桶
    0.09
    ç°ĩ
    0.09
    å°ĸ
    0.09
    æ¼Ķ
    0.09
    orate
    0.09
    åľ¨ç½ij绾
    0.09
    æļĩ
    0.09
    ervers
    0.09
    æĭŁ
    0.09
    Activations Density 0.300%

    No Known Activations