© 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. 4662
    Prev
    Next
    INDEX
    Explanations

    negative emotions and descriptors

    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
    ä¼łå¥ĩ
    -0.09
    æŁ¥æĺİ
    -0.09
    umba
    -0.09
    æ´¾
    -0.08
    oram
    -0.08
    ç²Ĵ
    -0.08
    åºĦåĽŃ
    -0.08
    åĿıäºĭ
    -0.08
    æ¶ī
    -0.08
    æµģåĩº
    -0.08
    POSITIVE LOGITS
    讨
    0.12
    éĢ¼
    0.12
    è¨İ
    0.11
    çªģåĩº
    0.10
    è¿«
    0.10
    追éĢIJ
    0.10
    计è¾ĥ
    0.10
    å¼łæī¬
    0.10
    åĴĦ
    0.10
    ç´łè´¨
    0.09
    Activations Density 0.061%

    No Known Activations