© 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. 57528
    Prev
    Next
    INDEX
    Explanations

    awareness, EFT, invention, new

    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
    éĢĨè¡Į
    -0.09
    omi
    -0.08
    æīĵ好
    -0.08
    éĢĶå¾Ħ
    -0.07
    è¹Ī
    -0.07
    rug
    -0.07
    åºĻ
    -0.07
    æīįèĥ½
    -0.07
    èĪª
    -0.07
    (++
    -0.07
    POSITIVE LOGITS
    让èĩªå·±
    0.10
    ä¸Ģ举
    0.10
    ä½łåĸľæ¬¢
    0.10
    ä¼´
    0.09
    åħ¨è¿ĩç¨ĭ
    0.09
    ä¸ĢåĪĨéĴŁ
    0.09
    æµģ失
    0.09
    ä¾ĭè¡Į
    0.09
    ä½ĵä¼ļ
    0.09
    ä¸Ģä¼ļåĦ¿
    0.09
    Activations Density 0.024%

    No Known Activations