© 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. 35207
    Prev
    Next
    INDEX
    Explanations

    evacuation

    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
    ä¸įåIJĥ
    -0.10
    åģļ大
    -0.09
    严åİīæīĵåĩ»
    -0.09
    类似çļĦ
    -0.09
    好åIJĥ
    -0.09
    å°Ŀ
    -0.09
    满äºĨ
    -0.09
     Susp
    -0.09
    olly
    -0.08
    åħļåĨħ
    -0.08
    POSITIVE LOGITS
    æĴ¤ç¦»
    0.20
    éĢĢåĩº
    0.19
     exit
    0.19
    éĢĥ离
    0.17
    æĴ¤
    0.17
     exits
    0.17
     Exit
    0.17
    éĢĥçĶŁ
    0.17
    exit
    0.16
     evac
    0.16
    Activations Density 0.072%

    No Known Activations