© 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. 9718
    Prev
    Next
    INDEX
    Explanations

    fear of

    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
    ì¶ĺ
    -0.11
    çĩĶ
    -0.10
    æĹ¢è¦ģ
    -0.10
    è¿Ļåĩłå¹´
    -0.10
    è¿Ļå¥Ĺ
    -0.10
    é¢Ľ
    -0.09
    è´¯éĢļ
    -0.09
    uess
    -0.09
    康
    -0.09
     rms
    -0.09
    POSITIVE LOGITS
    ç®Ĺ
    0.09
    ukt
    0.09
    ifer
    0.08
    ucker
    0.08
    梯
    0.08
     Cảnh
    0.08
    uku
    0.08
    VC
    0.08
    Delimiter
    0.08
    utton
    0.07
    Activations Density 0.018%

    No Known Activations