© 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. 39535
    Prev
    Next
    INDEX
    Explanations

    course of action

    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
    çĮĹ
    -0.10
    å®īåħ¨ä¿Ŀéļľ
    -0.10
    ç¼Ĺ
    -0.10
    éĺı
    -0.09
    å¹³åĿĩæ°´å¹³
    -0.09
    æ¦ľ
    -0.09
    èijŃ
    -0.09
    çĸĻ
    -0.09
    å·§
    -0.09
    çĶ¨èĩªå·±çļĦ
    -0.09
    POSITIVE LOGITS
    oved
    0.09
    estar
    0.09
    itor
    0.08
    wa
    0.08
    ourse
    0.08
    wij
    0.08
    .course
    0.08
     пÑĥÑĤи
    0.08
     course
    0.08
    itan
    0.08
    Activations Density 0.021%

    No Known Activations