© 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. 53716
    Prev
    Next
    INDEX
    Explanations

    is a question

    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
     meisten
    -0.11
    ä¹¾åĿ¤
    -0.10
    æŃ¢
    -0.09
    ius
    -0.08
     наÑĪи
    -0.08
    èĮ¹
    -0.08
     ÑĤеÑħнологии
    -0.08
     Kosten
    -0.08
    åѦä¼ļäºĨ
    -0.08
    管çIJĨä¸Ńå¿ĥ
    -0.08
    POSITIVE LOGITS
     stuff
    0.12
     инÑĦоÑĢмаÑĨиÑı
    0.11
     инÑĦоÑĢмаÑĨии
    0.10
    stuff
    0.10
     footage
    0.10
     множеÑģÑĤво
    0.10
    elts
    0.09
    ä¸Ģè§Ĵ
    0.09
    пÑĭ
    0.09
    åĢij
    0.09
    Activations Density 0.379%

    No Known Activations