© 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. 61939
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
    APO
    -0.10
    ito
    -0.09
     Consortium
    -0.09
    éĺĴ
    -0.09
    æīĵåĬ¨
    -0.09
    UCT
    -0.09
    æĺİçĻ½
    -0.09
    è¿Ļéĥ¨åĪĨ
    -0.09
    ä»ĭåħ¥
    -0.08
    æĩĤäºĭ
    -0.08
    POSITIVE LOGITS
    çĤ³
    0.09
    ç¥ŀå¥ĩ
    0.09
    符
    0.09
     affair
    0.09
    ç¾¤å²Ľ
    0.09
    山路
    0.08
    åĹ
    0.08
    ç¥ŀç§ĺ
    0.08
    èĹģ
    0.08
     Arabia
    0.08
    Activations Density 0.001%

    No Known Activations