© 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. 10399
    Prev
    Next
    INDEX
    Explanations

    adult services and performances

    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
    è¿ĻåĿĹ
    -0.11
    uten
    -0.10
    .src
    -0.09
    اتÙĩ
    -0.09
    æįķ
    -0.08
    论述
    -0.08
    èĺij
    -0.08
    çĦĸ
    -0.08
    änder
    -0.08
     investig
    -0.08
    POSITIVE LOGITS
    çļĩåIJİ
    0.09
    伶
    0.09
    æݨå¼Ģ
    0.09
    ÙĬÙĦÙĬ
    0.08
    éĺ¿å§¨
    0.08
    _fault
    0.08
    ê°Ŀ
    0.08
    人åijĺ
    0.08
    é¤IJ
    0.08
    aoke
    0.08
    Activations Density 0.023%

    No Known Activations