© 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. 23605
    Prev
    Next
    INDEX
    Explanations

    seems like everywhere

    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
    è§īå¾Ĺå¾Ī
    -0.11
    å¾Īåı¯èĥ½
    -0.10
     vo
    -0.09
    éĴ¿
    -0.09
    大éģĵ
    -0.09
    vo
    -0.09
    æķ¦
    -0.09
     ÑĦигÑĥÑĢ
    -0.08
    å¤ļä½į
    -0.08
    arna
    -0.08
    POSITIVE LOGITS
    æĢ»æľī
    0.11
    PathComponent
    0.10
    éĥ½æľīçĿĢ
    0.10
    è¦ģä¹Ī
    0.10
    è¶ĬæĿ¥è¶Ĭ
    0.09
    è¾ľè´Ł
    0.09
    æĢĢ
    0.09
    笼
    0.09
    ç³Ĭ
    0.09
    æ¢ĵ
    0.09
    Activations Density 0.063%

    No Known Activations