© 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. 9773
    Prev
    Next
    INDEX
    Explanations

    names ending in ski or sky

    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¸į说
    -0.10
    alic
    -0.10
    æŀŃ
    -0.09
    нÑĮ
    -0.09
    ÑĢаÑĦ
    -0.09
    ç°Ł
    -0.09
    ingham
    -0.09
    RIPT
    -0.09
    opia
    -0.09
    人åıĤ
    -0.09
    POSITIVE LOGITS
    æĸ¯åŁº
    0.13
    ski
    0.10
    sk
    0.10
    اس
    0.10
    Ñģкий
    0.10
    insky
    0.09
    æĪı
    0.09
    onder
    0.08
    [email
    0.08
    身边çļĦ
    0.08
    Activations Density 0.067%

    No Known Activations