© 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. 33271
    Prev
    Next
    INDEX
    Explanations

    legal and technical identifiers

    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
    éĿĽ
    -0.10
    æī§æķĻ
    -0.09
    éŨå¤ĸ
    -0.09
    è´©
    -0.08
    .Dot
    -0.08
     fallout
    -0.08
    éĶ¦
    -0.08
    èħĨ
    -0.08
    è¿ĽæĿ¥
    -0.08
    åĩºå¸Ńä¼ļè®®
    -0.08
    POSITIVE LOGITS
    èIJ¥åľ°
    0.11
    åľ°å½¢
    0.11
    èĥĮåĮħ
    0.11
    æ¯ı人
    0.11
     Backpack
    0.10
    åħ¨åijĺ
    0.09
    scopes
    0.09
    人身
    0.09
    ä¸ŃåįĪ
    0.09
    æ¯ı个人çļĦ
    0.09
    Activations Density 0.041%

    No Known Activations