© 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. 58821
    Prev
    Next
    INDEX
    Explanations

    pain relief and analgesia

    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
    ç®Ķ
    -0.09
    踪
    -0.09
    ç¨į
    -0.09
    olis
    -0.09
    æ´½
    -0.09
    æ¡Ī
    -0.08
    æĺĵäºİ
    -0.08
    leased
    -0.08
    йÑĤ
    -0.08
     precip
    -0.08
    POSITIVE LOGITS
    çĸ¼çĹĽ
    0.15
    çĹĽ
    0.12
     pain
    0.12
    çĹĽèĭ¦
    0.12
    çĹĽãģ¿
    0.12
     Pain
    0.11
    çĸ¼
    0.11
    pain
    0.11
    å¿įåıĹ
    0.10
    éĴĿ
    0.10
    Activations Density 0.091%

    No Known Activations