© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36177
    Prev
    Next
    INDEX
    Explanations

    vehicles and items

    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
    åĪ«
    -0.09
    erve
    -0.09
    dp
    -0.09
    åĪ¥
    -0.08
    è£Ķ
    -0.08
    人éĢī
    -0.08
    icit
    -0.08
    Junior
    -0.08
    ä¸įå·²
    -0.08
    åĪĽæĦı
    -0.08
    POSITIVE LOGITS
    缴è¾ĸ
    0.09
    éĿ¢çĽ®
    0.09
     lys
    0.08
    æľ¬èº«çļĦ
    0.08
    ific
    0.08
    омеÑĢ
    0.08
    urg
    0.08
    åŃĹ第
    0.08
    sville
    0.08
    æľ¬äºº
    0.08
    Activations Density 0.291%

    No Known Activations