© 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. 35813
    Prev
    Next
    INDEX
    Explanations

    kindness and gentleness

    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
    TEX
    -0.10
    å¾Īå¼Ģå¿ĥ
    -0.10
    pla
    -0.09
    æĦŁåºĶ
    -0.09
    swire
    -0.09
    ä¼ı
    -0.08
    æĦŁæĤŁ
    -0.08
    åĽº
    -0.08
    为æĤ¨
    -0.08
    åĽŀåij³
    -0.08
    POSITIVE LOGITS
    温æŁĶ
    0.14
     gent
    0.14
    gent
    0.12
     gentle
    0.12
    宽容
    0.11
    æŁĶ
    0.11
     Gentle
    0.11
    对å¾ħ
    0.10
     Gent
    0.10
    çľĭå¾ħ
    0.10
    Activations Density 0.024%

    No Known Activations