© 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. 63321
    Prev
    Next
    INDEX
    Explanations

    injury or absence

    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
    æ¯ıä½į
    -0.12
    æ¯ıä¸Ģä½į
    -0.11
    窳
    -0.11
    éĤ£äºĽ
    -0.10
    åºķèķ´
    -0.10
    çĬĬ
    -0.10
    æ·Ģ
    -0.10
    ayne
    -0.09
    ลาย
    -0.09
    ieten
    -0.09
    POSITIVE LOGITS
    请åģĩ
    0.08
    æľ¬æľŁ
    0.08
    ISE
    0.08
    orea
    0.08
    å½±
    0.08
    ä½ĵæ£Ģ
    0.08
    æľ¬æľĪ
    0.08
    occo
    0.07
    书éĿ¢
    0.07
    被
    0.07
    Activations Density 0.047%

    No Known Activations