© 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. 35951
    Prev
    Next
    INDEX
    Explanations

    university programs and internships

    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
    оÑģÑĮ
    -0.09
    emark
    -0.09
    æĻ®éĢļ人
    -0.08
    æ¯įåħ¬åı¸
    -0.08
    orz
    -0.08
    ocs
    -0.08
    åħ±åIJĮ
    -0.08
    Cour
    -0.08
    ripp
    -0.08
    ogene
    -0.08
    POSITIVE LOGITS
    å°ıçĭĹ
    0.10
    æĺ¥åŃ£
    0.09
    è¿Ļ份
    0.09
    ç¢ĵ
    0.09
    秣
    0.09
    åıĮæīĭ
    0.09
    秤
    0.08
    IZE
    0.08
    ä¸įåĥı
    0.08
    achts
    0.08
    Activations Density 0.114%

    No Known Activations