© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16882
    Prev
    Next
    INDEX
    Explanations

    conversion disorders and functional symptoms

    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
    çĮ·
    -0.10
     Mej
    -0.09
    纶
    -0.09
    åIJĦè¡Į
    -0.09
    ç¾¤å²Ľ
    -0.09
    æĤĶ
    -0.09
    _npc
    -0.09
     Architect
    -0.09
    rais
    -0.08
    ä¸į失
    -0.08
    POSITIVE LOGITS
    çĻĶ
    0.10
    çĦ¦èĻij
    0.10
    .requests
    0.08
    æĭľå¸Ī
    0.08
    èĩªåįij
    0.08
    èĩªåĬ©
    0.08
     ego
    0.08
    夸大
    0.08
     Rip
    0.08
     complaints
    0.08
    Activations Density 0.454%

    No Known Activations