© 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. 60608
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    Negative Logits
    esis
    -0.11
    å®ŀéĻħè¡ĮåĬ¨
    -0.09
    è¡ĮåĬ¨
    -0.09
    paces
    -0.08
    ysi
    -0.08
     action
    -0.08
    æĢĿæĥ³
    -0.08
    elan
    -0.08
    èĩªçĶ±
    -0.08
    ä¸Ģæŀ¶
    -0.08
    POSITIVE LOGITS
    ç»ıéªĮ
    0.14
    ç»ıéªĮåĴĮ
    0.14
     experience
    0.13
    ä½ĵéªĮ
    0.13
    æķĻè®Ń
    0.13
     Experience
    0.13
    ç¶ĵé©Ĺ
    0.12
    experience
    0.12
     experiences
    0.12
    _experience
    0.12
    Activations Density 0.070%

    No Known Activations