© 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. 7290
    Prev
    Next
    INDEX
    Explanations

    course or class contexts

    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
    /GPL
    -0.10
    ç¦ģ
    -0.09
     Hairst
    -0.09
    ä¹Łä¸įåı¯èĥ½
    -0.09
    椽
    -0.09
    .lat
    -0.09
    anken
    -0.09
    ment
    -0.09
    hair
    -0.08
    æ©Łæ§ĭ
    -0.08
    POSITIVE LOGITS
    æķĸ
    0.10
    ware
    0.09
    nal
    0.09
    çĥ
    0.09
    宽éĺĶ
    0.09
    Ware
    0.09
    ä¸Ģçĵ¶
    0.08
    æĪ¢
    0.08
    codec
    0.08
    éķľ
    0.08
    Activations Density 0.020%

    No Known Activations