© 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. 58556
    Prev
    Next
    INDEX
    Explanations

    feeling states and emotions

    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
    åı£åij³
    -0.09
    é»ijçĻ½
    -0.09
     вÑĭвод
    -0.09
     taste
    -0.09
    çħ¨
    -0.09
    &action
    -0.09
    èİ«åIJį
    -0.09
    çľĭä¸Ĭåİ»
    -0.09
    åij³éģĵ
    -0.08
     LAP
    -0.08
    POSITIVE LOGITS
    BSD
    0.10
    带ä¸Ĭ
    0.09
     Sund
    0.09
    é«¡
    0.09
    asin
    0.08
    tec
    0.08
    esus
    0.08
    ICAL
    0.08
    å¾ľ
    0.08
     Flour
    0.08
    Activations Density 0.012%

    No Known Activations