© 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. 37888
    Prev
    Next
    INDEX
    Explanations

    Alvarez vs

    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
    ä¸įå®Į
    -0.09
    èĢĺ
    -0.08
    umm
    -0.08
    outs
    -0.08
    ¼
    -0.08
    NING
    -0.08
    è¿ĩå¾Ĺ
    -0.08
    istent
    -0.08
    æĸ°å¾ģç¨ĭ
    -0.08
    ding
    -0.08
    POSITIVE LOGITS
    tn
    0.10
    antly
    0.09
    Õ¾
    0.09
    ly
    0.09
    ailable
    0.09
    æ»¨æ±Ł
    0.08
    гÑĢани
    0.08
    unner
    0.08
    mint
    0.08
     Serving
    0.08
    Activations Density 0.002%

    No Known Activations