© 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. 9291
    Prev
    Next
    INDEX
    Explanations

    larger than life, stage presence, star power

    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
    ç»ĦåĽ¾
    -0.10
    éĺ²å®Ī
    -0.10
    æįħ
    -0.09
    åŃĿ
    -0.09
    室åıĭ
    -0.09
     chop
    -0.08
     Sit
    -0.08
    éĹ°
    -0.08
    idor
    -0.08
    æīĭèĦļ
    -0.08
    POSITIVE LOGITS
    çľ¼çIJĥ
    0.10
    æŀ¶åŃIJ
    0.10
     personality
    0.09
    å¤¸å¼ł
    0.09
    大èĥĨ
    0.09
    ä»ĸæĺ¯ä¸Ģ个
    0.09
    LECT
    0.09
    èĢģ人家
    0.09
    åĩłåĪĨ
    0.09
    äººæł¼
    0.09
    Activations Density 0.154%

    No Known Activations