© 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. 18670
    Prev
    Next
    INDEX
    Explanations

    done/performed

    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
    çĪ±äºº
    -0.10
    /XMLSchema
    -0.09
    ç¼Ģ
    -0.09
     Bou
    -0.09
    å¯ĤéĿĻ
    -0.08
    åij¼
    -0.08
    宣åijĬ
    -0.08
    divide
    -0.08
    Lazy
    -0.08
    esco
    -0.08
    POSITIVE LOGITS
     done
    0.12
    	done
    0.11
    ä¸įåĪ°ä½į
    0.11
    å®ĮæĪIJåIJİ
    0.11
    Done
    0.10
    æĺ¯ä¸Ģ件
    0.10
     Done
    0.10
     erfol
    0.10
     performed
    0.10
    -done
    0.09
    Activations Density 0.933%

    No Known Activations