© 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. 23737
    Prev
    Next
    INDEX
    Explanations

    meet demand or needs

    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
    ä¸įä¸ĭ
    -0.09
     Companion
    -0.09
    пÑĭ
    -0.08
    æĥļ
    -0.08
     Las
    -0.08
    hof
    -0.08
    说æľį
    -0.08
    ilor
    -0.08
    las
    -0.08
     зÑĢ
    -0.08
    POSITIVE LOGITS
    满足
    0.21
    滿足
    0.18
    èĥ½æ»¡è¶³
    0.17
    å¸ĤåľºéľĢæ±Ĥ
    0.15
    客æĪ·éľĢæ±Ĥ
    0.15
    çļĦéľĢæ±Ĥ
    0.15
    æ¶Īè´¹éľĢæ±Ĥ
    0.14
    ä¾ĽåºĶ
    0.14
    éľĢæ±Ĥ
    0.14
     satisfaction
    0.13
    Activations Density 0.056%

    No Known Activations