© 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. 11377
    Prev
    Next
    INDEX
    Explanations

    liking someone or feelings for someone

    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
    ä¸įçĽ¸ä¿¡
    -0.10
    çĭ¡
    -0.09
    ä¸įä¿¡
    -0.09
    åIJ¾
    -0.09
    é¥ķ
    -0.09
    oven
    -0.09
    jis
    -0.08
    nio
    -0.08
    rze
    -0.08
    è²Ĥ
    -0.08
    POSITIVE LOGITS
    æģĭæĥħ
    0.15
     Crush
    0.15
     crush
    0.15
    女çĶŁ
    0.13
    表çĻ½
    0.13
    æģĭçĪ±
    0.13
    éĢĤ度
    0.11
    女åŃ©åŃIJ
    0.11
    å¿ĥ仪
    0.11
    å¿ĥ仪çļĦ
    0.10
    Activations Density 0.054%

    No Known Activations