© 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. 9319
    Prev
    Next
    INDEX
    Explanations

    Nicholas and Nicolas names

    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
    ëįĺ
    -0.10
    anga
    -0.08
    ness
    -0.08
    ecimal
    -0.08
    onas
    -0.08
    éļĻ
    -0.08
    uku
    -0.08
     wewnÄĻtrzn
    -0.08
    icket
    -0.08
    inand
    -0.08
    POSITIVE LOGITS
    ossal
    0.11
    angelo
    0.10
    ä½ĵåĪ¶æĶ¹éĿ©
    0.09
    çĿ¬
    0.09
    ands
    0.09
    xon
    0.09
    anton
    0.09
    Ñģон
    0.09
    ¤
    0.09
    ALLY
    0.09
    Activations Density 0.020%

    No Known Activations