© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36501
    Prev
    Next
    INDEX
    Explanations

    FIGHT or FLIGHT

    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
    æµ£
    -0.09
    è´´å¿ĥ
    -0.09
    pite
    -0.09
    äºŃ
    -0.09
    å¾Īæ¸ħæ¥ļ
    -0.09
    aal
    -0.08
    _ING
    -0.08
    å«©
    -0.08
    Hosting
    -0.08
    é¹Ĥ
    -0.08
    POSITIVE LOGITS
    ä¸īåĪĨ
    0.09
    踮
    0.09
    åģļ大åģļ强
    0.09
    ä¸ĢåĪĨ
    0.09
    æĺ¯æľĢ好çļĦ
    0.09
    åijĬ
    0.08
    åĩłåĪĨ
    0.08
    ä¸ĢåĪĨéĴŁ
    0.08
    综åIJĪæ²»çIJĨ
    0.08
    è¶Ĭæĺ¯
    0.08
    Activations Density 0.096%

    No Known Activations