© 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. 54450
    Prev
    Next
    INDEX
    Explanations

    experiencing negative outcomes or states

    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
    åIJ¬èµ·æĿ¥
    -0.08
    æĽ
    -0.08
    è´¡çĮ®
    -0.08
    åĶ§
    -0.08
    Looper
    -0.08
    æģ¯
    -0.08
    çīĩåŃIJ
    -0.08
    黣
    -0.08
    çĴĭ
    -0.08
    monster
    -0.08
    POSITIVE LOGITS
    èĦĶ
    0.10
     firsthand
    0.10
    æĪIJéķ¿
    0.10
    umba
    0.09
    æ´Ĺ礼
    0.09
    åīįæīĢæľª
    0.09
    åīįæīĢæľªæľī
    0.09
    acial
    0.09
    LOC
    0.09
    è£½ä½ľ
    0.09
    Activations Density 0.196%

    No Known Activations