© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55115
    Prev
    Next
    INDEX
    Explanations

    descriptive words

    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
    举æĬ¥çĶµè¯Ŀ
    -0.10
    åħ¢
    -0.09
    èĩªç§°
    -0.09
    æĪ¿ä¸ľ
    -0.09
    éĹªåħī
    -0.09
    ä¿Ń
    -0.09
    è¯
    -0.09
    èĿĩ
    -0.09
    èļĵ
    -0.09
    é£ŀæī¬
    -0.09
    POSITIVE LOGITS
    éħĿéħ¿
    0.09
    baugh
    0.09
    碧
    0.08
    contain
    0.08
    æĬļ
    0.08
    ç«łèĬĤ
    0.08
    åĭ¾
    0.08
    èĥĮæĻ¯
    0.08
    compact
    0.08
    panse
    0.08
    Activations Density 0.060%

    No Known Activations