© 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. 21426
    Prev
    Next
    INDEX
    Explanations

    quoted speech closing marks

    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
    fst
    -0.11
    综
    -0.10
    æĪij没æľī
    -0.09
    /o
    -0.09
    untas
    -0.09
    èѦåĬ¡
    -0.09
    .mutex
    -0.08
    æĪijåıªæĺ¯
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.08
    æĪijåı¯ä»¥
    -0.08
    POSITIVE LOGITS
    osh
    0.09
    æµ·åĨħå¤ĸ
    0.09
    éĿŀåĩ¡
    0.08
    éĻį
    0.08
    çIJĨ
    0.08
    éģµ
    0.08
    å¼ĢåıijåĪ©çĶ¨
    0.08
    ness
    0.08
    åĩĨåħ¥
    0.08
    bourg
    0.08
    Activations Density 0.052%

    No Known Activations