© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8670
    Prev
    Next
    INDEX
    Explanations

    meal composition, size, or patterns

    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
    enso
    -0.11
    gle
    -0.10
    oler
    -0.09
    辫
    -0.09
    ration
    -0.08
    éħ±
    -0.08
    åİĨå¹´
    -0.08
    TRS
    -0.08
    encer
    -0.08
    gere
    -0.08
    POSITIVE LOGITS
    éĢĴ
    0.09
    è´¬
    0.09
    çŨ
    0.09
    éĢĴç»Ļ
    0.09
    worm
    0.08
    ä½Ĩæĺ¯æĪij
    0.08
    .Imp
    0.08
     NotImplemented
    0.08
    诽
    0.08
    éĥ´å·ŀ
    0.08
    Activations Density 0.006%

    No Known Activations