© 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. 23356
    Prev
    Next
    INDEX
    Explanations

    conflict or collision

    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
    Ñħод
    -0.09
    oger
    -0.09
    ж
    -0.09
    ç¾İåĮĸ
    -0.09
    eut
    -0.09
    apolis
    -0.09
    æł·åŃIJ
    -0.08
    åŁĴ
    -0.08
    cef
    -0.08
    Ī
    -0.08
    POSITIVE LOGITS
    ingly
    0.13
    ordova
    0.10
    nable
    0.10
    èĮĦ
    0.10
    zyst
    0.09
    Occurred
    0.09
    ently
    0.09
    idden
    0.09
    åħķ
    0.09
    æĬ¢
    0.09
    Activations Density 0.007%

    No Known Activations