© 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. 57493
    Prev
    Next
    INDEX
    Explanations

    social links and buttons

    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
    æĪ¾
    -0.10
    çģµæĦŁ
    -0.09
    åīįåĩłå¤©
    -0.09
     bÄĥng
    -0.09
    ä¸Ĭå¹´åIJĮæľŁ
    -0.09
    ÑģÑĢ
    -0.09
    åĿIJä¸ĭ
    -0.09
     пÑģ
    -0.09
    çݺ
    -0.09
    olina
    -0.08
    POSITIVE LOGITS
    纷纷
    0.08
    jer
    0.08
    ret
    0.08
    èħĨ
    0.08
    æ³°å±±
    0.08
     Kur
    0.08
    ä¸ij
    0.08
    å¿ĥçIJĨ
    0.08
     GI
    0.08
     sdl
    0.08
    Activations Density 0.003%

    No Known Activations