© 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. 49850
    Prev
    Next
    INDEX
    Explanations

    myasthenia, esterase, voltage-gated, acetylcholine

    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
    æ£ī
    -0.11
    æģ
    -0.09
     flats
    -0.09
    tweet
    -0.09
    大声
    -0.09
     Cres
    -0.09
    åĸ³
    -0.08
    åĨ»
    -0.08
    æŁĶ
    -0.08
    _Inter
    -0.08
    POSITIVE LOGITS
     Directorate
    0.11
    æ¸Ĭ
    0.11
    åĿŀ
    0.10
    交éĢļæŀ¢çº½
    0.10
    æĺ¾
    0.09
    è§Ĩ线
    0.09
    åıĪ被
    0.08
    åѵåĮĸ
    0.08
    ons
    0.08
    æĹ©æĻ¨
    0.08
    Activations Density 0.179%

    No Known Activations