© 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. 39934
    Prev
    Next
    INDEX
    Explanations

    focusing on 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
    å¤ļãģı
    -0.09
    ashing
    -0.09
    èįī
    -0.08
    çĻ¾ç§ij
    -0.08
    çļĦ姿æĢģ
    -0.08
    unu
    -0.08
    äºĭå®ŀ
    -0.08
     Rash
    -0.08
     rundown
    -0.08
    iti
    -0.08
    POSITIVE LOGITS
    åĬ¨æľº
    0.17
     motivation
    0.16
    æ¿ĢåĬ±
    0.12
    åĬ¨åĬĽ
    0.12
     motiv
    0.12
     motivate
    0.11
    çļĦåĬ¨åĬĽ
    0.11
     motivating
    0.11
    驱
    0.11
    缮æ¨Ļ
    0.11
    Activations Density 0.096%

    No Known Activations