© 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. 55219
    Prev
    Next
    INDEX
    Explanations

    injury or damage

    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
    åłµ
    -0.11
    ä¸ĭåįĬ
    -0.11
    çĸ¼çĹĽ
    -0.10
    伤åı£
    -0.10
    çIJĨ
    -0.09
    ıt
    -0.09
    еÑĢе
    -0.08
    积水
    -0.08
    èĥ¤
    -0.08
    çĶļèĩ³è¿ĺ
    -0.08
    POSITIVE LOGITS
    åľ¨ä»Ĭå¹´
    0.09
    arak
    0.09
    ãģ£ãģįãĤĬ
    0.09
     Sark
    0.09
    诡
    0.08
     Pers
    0.08
    å®ĹæķĻ
    0.08
    raud
    0.08
    ä¸Ģå¹´å¤ļ
    0.08
     Religious
    0.08
    Activations Density 0.158%

    No Known Activations