© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21328
    Prev
    Next
    INDEX
    Explanations

    way

    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
    çIJ¥
    -0.10
    为主ä½ĵ
    -0.09
    asha
    -0.09
    obia
    -0.08
    iliated
    -0.08
    rika
    -0.08
    ERICA
    -0.08
     bol
    -0.08
    âŀ
    -0.08
    建åĨĽ
    -0.08
    POSITIVE LOGITS
    åĩºè·¯
    0.14
    éĢĶ
    0.10
    çªģçł´åı£
    0.09
    请èģĶç³»
    0.09
    涯
    0.09
    еж
    0.08
    éĢĶå¾Ħ
    0.08
    å´ĸ
    0.08
    æĬĺåıł
    0.08
    è·¯å¾Ħ
    0.08
    Activations Density 0.046%

    No Known Activations