© 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. 19504
    Prev
    Next
    INDEX
    Explanations

    that's what

    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
    æıIJåIJį
    -0.11
    اÙĪ
    -0.10
    çIJ¬
    -0.09
     еÑīÑij
    -0.09
    对åħ¬åı¸
    -0.09
    æĺ¯æĪij们
    -0.09
    å§IJ
    -0.09
    çªł
    -0.09
    .symmetric
    -0.08
    åı¯ä»¥è®©
    -0.08
    POSITIVE LOGITS
    çĽij管éĥ¨éŨ
    0.11
    opal
    0.10
    Ãły
    0.09
    桶
    0.09
    å½ĵä½ł
    0.08
    å®ŀå®ŀåľ¨åľ¨
    0.08
    ç»Ŀ大å¤ļæķ°
    0.08
    ographies
    0.08
    人éĹ´
    0.08
     nin
    0.08
    Activations Density 0.090%

    No Known Activations