© 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. 54525
    Prev
    Next
    INDEX
    Explanations

    emotional reactions to events

    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
    åīª
    -0.09
    olem
    -0.09
    /the
    -0.08
    think
    -0.08
    wide
    -0.08
    羣æŃ£
    -0.08
    æļ¨
    -0.08
    èĮĮ
    -0.07
    ãģĪ
    -0.07
     sentiment
    -0.07
    POSITIVE LOGITS
    ness
    0.16
    NESS
    0.12
    ä¸įå·²
    0.11
    ISON
    0.10
     tot
    0.10
    è¿Ļæĺ¯ä¸Ģ个
    0.10
    å®ĥæĺ¯
    0.10
    رÙĨ
    0.10
    åľ°è¯´
    0.09
    é£İåIJ¹
    0.09
    Activations Density 0.076%

    No Known Activations