© 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. 36090
    Prev
    Next
    INDEX
    Explanations

    above, below, bottom, top, base, over

    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
     buc
    -0.09
    mony
    -0.09
     sep
    -0.08
    è¿ĩæĿ¥
    -0.08
    æ¯ģ
    -0.08
    ษ
    -0.08
     Robbins
    -0.08
    isphere
    -0.08
    wards
    -0.08
     Vic
    -0.08
    POSITIVE LOGITS
    éĵŃ
    0.10
    訴
    0.09
    åĴĴ
    0.09
    ilen
    0.09
    èij¶
    0.09
    .Marker
    0.09
    çIJĨäºĭä¼ļ
    0.08
    éĤĻ
    0.08
    éĽĨåĽ¢èĤ¡ä»½
    0.08
    éĻIJ度
    0.08
    Activations Density 0.083%

    No Known Activations