© 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. 3825
    Prev
    Next
    INDEX
    Explanations

    symptoms and signs

    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
    æµĨ
    -0.09
    alach
    -0.09
     mùi
    -0.09
    å¾Ļ
    -0.09
    mor
    -0.09
    æ³¾
    -0.08
    ulence
    -0.08
    åij³éģĵ
    -0.08
    Scoped
    -0.08
    æijĩ
    -0.08
    POSITIVE LOGITS
    åIJĦæł·
    0.11
    è¯ĬæīĢ
    0.10
    ston
    0.10
    åĪĨåĪ«æĺ¯
    0.10
     common
    0.10
    ä¸ŃåĽ½åı¤ä»£
    0.09
    主åĬ¨
    0.09
    ä½ķå¿ħ
    0.09
    ä¸Ľä¹¦
    0.09
    éĹ³
    0.09
    Activations Density 0.153%

    No Known Activations