© 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. 33243
    Prev
    Next
    INDEX
    Explanations

    court opinions, sealed documents

    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
    åĿ¦
    -0.12
    urg
    -0.10
    èĥĨ
    -0.10
     dec
    -0.09
     cand
    -0.09
    ç©ij
    -0.08
    UR
    -0.08
    T
    -0.08
     Chand
    -0.08
     keys
    -0.08
    POSITIVE LOGITS
    æİ¥éĢģ
    0.10
    anium
    0.10
    âľĸ
    0.10
    åĽºåĮĸ
    0.10
     Closed
    0.09
    éģ®
    0.09
    æ´Ħ
    0.09
    childs
    0.09
    ç»Ļå®Ŀå®Ŀ
    0.09
    åħ·ä½ĵåĨħ容
    0.09
    Activations Density 0.031%

    No Known Activations