© 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. 55963
    Prev
    Next
    INDEX
    Explanations

    morale and motivation

    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
    éĢłç¦ı
    -0.10
    绡
    -0.09
    ä»ĺåĩº
    -0.09
     Crazy
    -0.09
    çıł
    -0.09
    ç®Ģ约
    -0.09
    ç´
    -0.08
    _js
    -0.08
    earing
    -0.08
    è¶ħæłĩ
    -0.08
    POSITIVE LOGITS
    ä¿¡å¿ĥ
    0.20
     morale
    0.19
    æĸĹå¿Ĺ
    0.17
    é¼ĵèĪŀ
    0.17
    çļĦä¿¡å¿ĥ
    0.17
    士
    0.16
    æ²®
    0.14
    人å¿ĥ
    0.14
     spirits
    0.14
     confidence
    0.14
    Activations Density 0.054%

    No Known Activations