© 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. 61064
    Prev
    Next
    INDEX
    Explanations

    hash related terms

    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
    欲
    -0.09
     tắc
    -0.09
    urer
    -0.08
    oplast
    -0.08
    éļĶ
    -0.08
    æīĢæīĢ
    -0.08
    çŀ©
    -0.08
    angel
    -0.08
    تب
    -0.08
    çģ¼
    -0.08
    POSITIVE LOGITS
    0.12
    imoto
    0.12
    èIJ½ãģ¡
    0.10
    å²ĸ
    0.10
    æ»ĵ
    0.10
    æĪIJ年人
    0.10
    /hash
    0.09
    ç»ĵæŀľæĺ¾ç¤º
    0.09
    çij¢
    0.09
    ede
    0.09
    Activations Density 0.054%

    No Known Activations