© 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. 21073
    Prev
    Next
    INDEX
    Explanations

    names ending in wick or wich

    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
    вин
    -0.10
    VENT
    -0.10
    éĢļé£İ
    -0.10
     волн
    -0.10
    ials
    -0.10
    ParallelGroup
    -0.09
    ãģĦãģĨ
    -0.09
    BitFields
    -0.09
    弦
    -0.09
     ÐĴлад
    -0.09
    POSITIVE LOGITS
    ro
    0.09
    ings
    0.09
    RITE
    0.08
    robe
    0.08
    åŃIJéĩĮ
    0.08
     hứng
    0.08
    ä¸ĭåįĬ
    0.08
    ä½ķåĨµ
    0.08
    salt
    0.08
    éĨ®
    0.08
    Activations Density 0.006%

    No Known Activations