© 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. 39442
    Prev
    Next
    INDEX
    Explanations

    library

    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
    éĻIJéĩı
    -0.10
    秽
    -0.09
    éĢŀ
    -0.09
    åIJł
    -0.09
    èĪįä¸įå¾Ĺ
    -0.09
    è¿ĺåı¯
    -0.09
    æ³£
    -0.09
    downloads
    -0.09
    ìłĪ
    -0.08
    YPE
    -0.08
    POSITIVE LOGITS
    æĬ¬å¤´
    0.09
    èĥ¸
    0.08
    onne
    0.08
    åIJijåīį
    0.08
    ä»°
    0.08
    iac
    0.08
    éĺ¶çº§
    0.08
    /photos
    0.07
     prow
    0.07
    oured
    0.07
    Activations Density 0.011%

    No Known Activations