© 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. 38421
    Prev
    Next
    INDEX
    Explanations

    something to do with

    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
     reass
    -0.09
    ovi
    -0.09
    ÙĬÙĪ
    -0.09
    	Copyright
    -0.09
    LIKE
    -0.09
     Raz
    -0.08
    illow
    -0.08
    èªŃãģ¿
    -0.08
     principal
    -0.08
    hog
    -0.08
    POSITIVE LOGITS
    æĹłåħ³
    0.15
     unrelated
    0.10
    æ¶īåıĬåĪ°
    0.10
     matters
    0.10
    åħ³ä¹İ
    0.10
    æīĵ交éģĵ
    0.09
    éĸ¢ãĤı
    0.09
    äºĭ项
    0.09
    ä¹İ
    0.09
     ÙĬتعÙĦÙĤ
    0.09
    Activations Density 0.037%

    No Known Activations