© 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. 62591
    Prev
    Next
    INDEX
    Explanations

    asking why

    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
    çľĭä¸įè§ģ
    -0.09
    ä¸įèĩ³äºİ
    -0.09
    èµĶ
    -0.09
    ä¸įå¤Ł
    -0.09
    ::$
    -0.08
    ãģĤãĤĬ
    -0.08
    likelihood
    -0.08
    &view
    -0.08
    èĴĮ
    -0.08
     Desk
    -0.08
    POSITIVE LOGITS
    åĩĮ
    0.12
    åıįæŃ£
    0.11
    æĢ»ä¹ĭ
    0.11
    shr
    0.10
    æ¸łéģĵ
    0.10
    åħ¨ç¤¾ä¼ļ
    0.10
    åĢ¨
    0.09
    ä¹Łæ²¡æľī
    0.09
    çĸ²
    0.09
    åĹĵ
    0.09
    Activations Density 0.060%

    No Known Activations