© 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. 33434
    Prev
    Next
    INDEX
    Explanations

    in advance

    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
    ç´¯äºĨ
    -0.10
    ä¸įå°½
    -0.10
    aoke
    -0.10
    èĥ¥
    -0.09
    threads
    -0.09
    家å±ŀ
    -0.09
    éģĹæ¼ı
    -0.09
    /cgi
    -0.09
    æѤæŶ
    -0.09
    å±ŀ
    -0.09
    POSITIVE LOGITS
    /current
    0.12
    -looking
    0.10
    ANCE
    0.10
    [next
    0.09
    emente
    0.09
    çļĦæĹ¥åŃIJéĩĮ
    0.09
    å·¥ä½ľä¸Ń
    0.09
    峪
    0.09
    ceptor
    0.08
    ively
    0.08
    Activations Density 0.008%

    No Known Activations