© 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. 20761
    Prev
    Next
    INDEX
    Explanations

    discriminating, perfectionist, fussy

    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
     possibility
    -0.09
     Deng
    -0.09
    æģ¯
    -0.08
    ARAM
    -0.08
    éľĦ
    -0.08
    /io
    -0.08
    å®Ĺ
    -0.08
    ä¸ĺ
    -0.08
    ames
    -0.08
    icare
    -0.08
    POSITIVE LOGITS
    èĭĽ
    0.13
    æĮijåīĶ
    0.11
    å®Įç¾İçļĦ
    0.10
    å®Įç¾İ
    0.09
    iest
    0.09
    认为
    0.09
    åı£åij³
    0.09
    tical
    0.09
    itis
    0.09
     ÙĦÙĦغاÙĬØ©
    0.09
    Activations Density 0.018%

    No Known Activations