© 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. 11894
    Prev
    Next
    INDEX
    Explanations

    personal opinions and outcomes

    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
    æĶ¸
    -0.10
    лов
    -0.10
    红åĨĽ
    -0.09
    åijĬè¯īæĪij们
    -0.09
     Rosenberg
    -0.09
    HIR
    -0.09
    otton
    -0.09
    ä¸įåı¯æĪĸ缺
    -0.09
    моÑĤ
    -0.08
    enti
    -0.08
    POSITIVE LOGITS
     outcome
    0.12
    è´¨éĩıåĴĮ
    0.10
    çľ¼åīįçļĦ
    0.10
    åīįæĻ¯
    0.10
    çİ°çĬ¶
    0.09
     situation
    0.09
    åıijå±ķåīįæĻ¯
    0.09
    å¾ħéģĩ
    0.09
    é¢IJ
    0.09
     prospects
    0.09
    Activations Density 0.064%

    No Known Activations