© 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. 61752
    Prev
    Next
    INDEX
    Explanations

    civil rights advocate/activist/violation/action

    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
    mith
    -0.10
     bầu
    -0.10
    DED
    -0.10
    ä¸Ģå¹´ä¸Ģ度
    -0.09
    ä¸Ńæŀ¢
    -0.09
    å°±å¾Ī
    -0.09
    ä»Ļå¢ĥ
    -0.09
    åħ¨çIJĥ
    -0.09
    èįīåĿª
    -0.09
    ãģĦãģŁ
    -0.09
    POSITIVE LOGITS
    -era
    0.12
    orz
    0.09
    èĤĭ
    0.08
    uite
    0.08
    oris
    0.08
     era
    0.08
    串
    0.08
    伸
    0.08
    æĹ¶ä»£çļĦ
    0.08
    ç»ĦåĽ¾
    0.08
    Activations Density 0.004%

    No Known Activations