© 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. 9134
    Prev
    Next
    INDEX
    Explanations

    advance, evaluating, attracting, supply

    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
    ä½³
    -0.10
    ç²¾åįİ
    -0.09
    aida
    -0.08
     Saf
    -0.08
    ropa
    -0.08
    MAND
    -0.08
    åIJŁ
    -0.08
    ãĥĪãĥ©
    -0.08
    Slow
    -0.08
    å²ĺ
    -0.07
    POSITIVE LOGITS
    æ´ĭæ´ĭ
    0.10
    èĩªèIJ¥
    0.08
    å¸ĤæĶ¿åįı
    0.08
     pros
    0.08
    ivable
    0.08
    æ§Ĭ
    0.08
    éĢ¼è¿ij
    0.08
    ä½Ľå±±
    0.08
    sville
    0.08
    å¢ĥ
    0.08
    Activations Density 0.346%

    No Known Activations