© 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. 53618
    Prev
    Next
    INDEX
    Explanations

    settlement, treaty, deal

    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
    èĩªæľī
    -0.11
    ender
    -0.09
    ENDER
    -0.09
    ledge
    -0.09
    esting
    -0.08
    强大çļĦ
    -0.08
    rote
    -0.08
     camping
    -0.08
     eros
    -0.08
    inish
    -0.08
    POSITIVE LOGITS
    解åĨ³æĸ¹æ¡Ī
    0.14
    åĩºè·¯
    0.12
    解åĨ³éĹ®é¢ĺ
    0.11
    解åĨ³
    0.10
    解決
    0.10
    溶液
    0.10
     solution
    0.10
     ÑĢеÑĪениÑı
    0.10
    æĹ©æĹ¥
    0.10
     solutions
    0.10
    Activations Density 0.058%

    No Known Activations