© 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. 58557
    Prev
    Next
    INDEX
    Explanations

    open-mindedness

    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
    ä½łèĩªå·±
    -0.12
    æĪijèĩªå·±
    -0.12
    ä»ĸèĩªå·±
    -0.11
    è¿ĺåİŁ
    -0.10
    èįĩ
    -0.10
     ìĦľë¡ľ
    -0.09
    çļĦçĶ·äºº
    -0.09
     mutual
    -0.09
     ÑģебÑı
    -0.09
    oret
    -0.09
    POSITIVE LOGITS
    æĶ¹éĿ©åĪĽæĸ°
    0.09
    æĦīå¿«
    0.08
    ä¸ĢéŨ
    0.08
    çī¹çĤ¹
    0.08
    çĻ½çĻ½
    0.08
    åįļ
    0.08
    alias
    0.08
     ÑģÑĥд
    0.08
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.08
    zen
    0.07
    Activations Density 1.264%

    No Known Activations