© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58522
    Prev
    Next
    INDEX
    Explanations

    launched, held, can

    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
    ãģĦãģĨ
    -0.10
    享åıĹåĪ°
    -0.10
    egov
    -0.10
     wikipedia
    -0.10
    íģIJ
    -0.09
    ðŁĴĻ
    -0.09
    adget
    -0.09
    requested
    -0.09
    _SIG
    -0.09
    ÄIJT
    -0.09
    POSITIVE LOGITS
    æļ¨
    0.10
    ä¸Ģçľ¼
    0.10
     ниÑĩ
    0.09
    表éĿ¢ä¸Ĭ
    0.09
    åIJİèĢħ
    0.09
    æĺ¥å¤ı
    0.08
     Lance
    0.08
    веÑģ
    0.08
    åĵªä¸Ģ个
    0.08
    æĺ¥å¤©
    0.08
    Activations Density 0.061%

    No Known Activations