© 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. 22715
    Prev
    Next
    INDEX
    Explanations

    negative outcomes 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
    ugi
    -0.09
    æµħ
    -0.08
    临æŶ
    -0.08
    ANTE
    -0.08
     GLint
    -0.08
    оÑĩно
    -0.08
    éĵł
    -0.08
    iale
    -0.08
     Commerce
    -0.08
    imet
    -0.08
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.12
    绾
    0.09
    DidLoad
    0.09
    åħī彩
    0.09
    ä¸įæŃ»
    0.09
    é¢ł
    0.09
    év
    0.08
    çŃĭ
    0.08
    OLUM
    0.08
     Griffith
    0.08
    Activations Density 0.079%

    No Known Activations