© 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. 57027
    Prev
    Next
    INDEX
    Explanations

    punk rock

    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
    毯
    -0.09
    æĭ©
    -0.09
    樵
    -0.09
    (big
    -0.08
     viz
    -0.08
     Buzz
    -0.08
    äºĴèģĶ
    -0.08
    escort
    -0.08
     Credits
    -0.08
    é©»
    -0.08
    POSITIVE LOGITS
    èį·
    0.09
    éĢĢç¨İ
    0.09
    -animate
    0.09
    é¢Ĩ
    0.08
    .CR
    0.08
    ç°§
    0.08
    .mb
    0.08
    templ
    0.08
    æijĩ
    0.08
     nob
    0.08
    Activations Density 0.147%

    No Known Activations