© 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. 18777
    Prev
    Next
    INDEX
    Explanations

    greeting and question

    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´ŀ
    -0.09
    ugar
    -0.09
    æĦıæĥ³ä¸įåĪ°
    -0.09
    uggy
    -0.09
    [size
    -0.08
     OTHERWISE
    -0.08
    orque
    -0.08
    ICLE
    -0.08
    [url
    -0.08
    ILED
    -0.08
    POSITIVE LOGITS
    éĤ£ä½ł
    0.10
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    çĪĨ
    0.08
    ë©ĺ
    0.08
    way
    0.08
    isci
    0.08
    lane
    0.08
    inen
    0.08
    çļĦç¡®
    0.08
    ä½łåı¯ä»¥
    0.08
    Activations Density 0.057%

    No Known Activations