© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20001
    Prev
    Next
    INDEX
    Explanations

    unite, unity, united

    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
    sey
    -0.09
    åĿŀ
    -0.09
    razier
    -0.08
    æĪijä¸Ģ缴
    -0.08
    alous
    -0.08
    noon
    -0.08
    inkel
    -0.08
    overe
    -0.08
    缼ä¸ĸ
    -0.08
    ä½ĵçİ°åĩº
    -0.08
    POSITIVE LOGITS
    人å¿ĥ
    0.11
    èµ·æĿ¥
    0.11
    åīĤ
    0.11
    åľ¨ä¸Ģèµ·
    0.10
    aries
    0.09
    éľĨ
    0.09
    èĪ°éĺŁ
    0.09
    LEV
    0.09
    erras
    0.09
    ement
    0.09
    Activations Density 0.044%

    No Known Activations