© 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. 50316
    Prev
    Next
    INDEX
    Explanations

    and subsequent outcomes

    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
     ÑĢазвива
    -0.09
    çŁ¥éģĵèĩªå·±
    -0.09
    ä¸įèĥ½åĨį
    -0.09
    ä»ģ
    -0.09
    éĵ¢
    -0.09
    èĩªå·±çļĦ
    -0.08
    çĪ±å¥½
    -0.08
    èįı
    -0.08
    æīįèĥ½å¤Ł
    -0.08
    驾车
    -0.08
    POSITIVE LOGITS
    带æĿ¥
    0.14
    åħģ许
    0.13
    让æĤ¨
    0.13
    ä¹Łè®©
    0.12
    使åħ¶
    0.12
    æıIJä¾ĽäºĨ
    0.12
    使
    0.12
     allow
    0.12
    带æĿ¥äºĨ
    0.12
    帮åĬ©
    0.11
    Activations Density 0.288%

    No Known Activations