© 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. 33340
    Prev
    Next
    INDEX
    Explanations

    Math, Garden, Club, Lang, Boorai

    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
    ulous
    -0.09
    ToF
    -0.08
    ooth
    -0.08
     дома
    -0.08
    zie
    -0.08
    itur
    -0.08
     CLUB
    -0.08
    uly
    -0.08
    kek
    -0.07
    å©´
    -0.07
    POSITIVE LOGITS
    建æĪIJåIJİ
    0.12
    è§Ħç«łåĪ¶åº¦
    0.10
    å¹³æŶ
    0.10
    对å¤ĸå¼ĢæĶ¾
    0.10
    å§ĭ建äºİ
    0.10
    æ¯ıå¹´
    0.09
     vicinity
    0.09
    å¡ijèĥ¶
    0.09
    设æĸ½
    0.09
    åĿĢ
    0.09
    Activations Density 0.172%

    No Known Activations