© 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. 27159
    Prev
    Next
    INDEX
    Explanations

    positive emotions and looking forward

    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
    éĤ»éĩĮ
    -0.09
    çīµ
    -0.09
    马æĿ¥
    -0.08
    icut
    -0.08
    -int
    -0.08
    IC
    -0.08
    è¹ĩ
    -0.08
    æķ£æĸĩ
    -0.08
    åľĪåŃIJ
    -0.08
    ä¸ĢåľĪ
    -0.08
    POSITIVE LOGITS
     lắm
    0.09
    erra
    0.09
    abal
    0.09
    /sites
    0.09
    åĢĴæĺ¯
    0.09
    åĴ¥
    0.09
    Pont
    0.08
    -SA
    0.08
    æĥº
    0.08
    æĤ²
    0.08
    Activations Density 0.017%

    No Known Activations