© 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. 38465
    Prev
    Next
    INDEX
    Explanations

    recreational activities and purposes

    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
    ä¿¡ç®±
    -0.09
     sling
    -0.09
    ç¾¹
    -0.09
    archy
    -0.09
    èĽ¸
    -0.09
    ains
    -0.08
    oston
    -0.08
    Å®
    -0.08
    ToOne
    -0.08
    iani
    -0.08
    POSITIVE LOGITS
    娱ä¹IJ
    0.10
    çİ©èĢį
    0.10
    娱
    0.09
    é¢ł
    0.09
    nier
    0.09
    举é£İ
    0.09
    æĸĩ娱
    0.09
     cru
    0.08
    æĪIJéķ¿ä¸º
    0.08
    çĶ¨åľ°
    0.08
    Activations Density 0.013%

    No Known Activations