© 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. 55342
    Prev
    Next
    INDEX
    Explanations

    adverse safety effects and tolerability

    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
    é«ĺéĢŁ
    -0.09
    è¡Ķ
    -0.09
    é¼İ
    -0.09
    æľī两ç§į
    -0.08
    ç·
    -0.08
    ç¼ĺåĪĨ
    -0.08
    é¦ı
    -0.08
    üs
    -0.08
    å§Ĭ妹
    -0.08
    åĸĭ
    -0.08
    POSITIVE LOGITS
    å®īåħ¨æĢ§
    0.10
    èĩ´åij½
    0.09
    åħ¨åijĺ
    0.09
    -reported
    0.09
    æĬ¥åijĬæľŁåĨħ
    0.08
    .side
    0.08
    anoi
    0.08
    æģ¶å¿ĥ
    0.08
    ç¯Ŀ
    0.08
    BOSE
    0.08
    Activations Density 0.153%

    No Known Activations