© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35665
    Prev
    Next
    INDEX
    Explanations

    personal touch or treatment

    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
    ä½ĨæĪij
    -0.09
     Bron
    -0.08
    稳妥
    -0.08
    åı¯è°ĵ
    -0.08
    ä¸į平衡
    -0.08
     Hum
    -0.08
    asca
    -0.08
    quip
    -0.08
    åĻ¨åħ·
    -0.08
     POL
    -0.08
    POSITIVE LOGITS
    åħ·ä½ĵæĥħåĨµ
    0.10
    亲
    0.10
    åħ³æ³¨
    0.10
    çļĦåħ³æ³¨
    0.10
    ynth
    0.10
    æ¸İ
    0.10
    亲èĩª
    0.09
    ystone
    0.09
     personally
    0.09
    æĦŁæĥħ
    0.09
    Activations Density 0.017%

    No Known Activations