© 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. 50209
    Prev
    Next
    INDEX
    Explanations

    file extensions like .css, .js, .py, .txt

    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
    CTR
    -0.09
    ENCY
    -0.09
     Cul
    -0.09
    anic
    -0.08
    ftime
    -0.08
    æ²ī
    -0.08
    åIJİæŀľ
    -0.08
    è´§æŀ¶
    -0.08
    æłı缮
    -0.08
    å¸ĮæľĽå¤§å®¶
    -0.08
    POSITIVE LOGITS
    .py
    0.12
    README
    0.11
    æŃ£éĿ¢
    0.10
    .txt
    0.10
    å¿ħä¸įåı¯
    0.10
     невоз
    0.09
    æ±ĩæĢ»
    0.09
    .js
    0.09
    .tpl
    0.09
    éĤĪ
    0.09
    Activations Density 1.544%

    No Known Activations