© 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. 30132
    Prev
    Next
    INDEX
    Explanations

    clarify when or if

    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
    erness
    -0.10
    ness
    -0.10
    .Singleton
    -0.10
    sville
    -0.10
    çĿ¨
    -0.10
    è°ı
    -0.09
    NESS
    -0.09
    建åįİ
    -0.09
    ç»ıéªĮåĴĮ
    -0.09
    éĢĢåĽŀ
    -0.09
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.15
    ä¸Ģä¸ĭ
    0.12
    äºĨä¸Ģä¸ĭ
    0.10
    æ¾Ħæ¸ħ
    0.10
    è¨ĢãģĪãģ°
    0.09
    ìĤ¬íķŃ
    0.09
    fy
    0.09
    æ»ĵ
    0.09
    äºĨä¸įå°ij
    0.08
    误ä¼ļ
    0.08
    Activations Density 0.019%

    No Known Activations