© 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. 34518
    Prev
    Next
    INDEX
    Explanations

    allergic reactions

    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
    è·Łå¥¹
    -0.09
    诱åıij
    -0.09
    uther
    -0.08
    obot
    -0.08
     NT
    -0.08
    elder
    -0.08
    .dtd
    -0.08
     Meyer
    -0.08
    ç§ĭåĨ¬
    -0.08
    hor
    -0.08
    POSITIVE LOGITS
    座
    0.10
    .EMPTY
    0.10
    åĸī
    0.09
    ç¥ī
    0.09
    _bh
    0.09
    æ¥ļ
    0.09
    è½²
    0.09
    鬼
    0.09
    èĤ¸
    0.09
    èı½
    0.08
    Activations Density 0.019%

    No Known Activations