© 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. 56080
    Prev
    Next
    INDEX
    Explanations

    bravery and courage

    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
    æĿµ
    -0.10
    è¿ĩ度
    -0.09
    延éķ¿
    -0.09
    fel
    -0.08
    毡
    -0.08
    ĸī
    -0.08
    hra
    -0.08
    åģ¶
    -0.08
    é¢ĵ
    -0.08
    ilation
    -0.08
    POSITIVE LOGITS
    åĭĩæ°Ķ
    0.31
    èĥĨ
    0.24
     courage
    0.21
    èĨ½
    0.19
    åĭĩæķ¢
    0.18
    éŃĦ
    0.17
     Courage
    0.16
    åĨ³å¿ĥ
    0.15
    æķ¢äºİ
    0.15
    åĭĩ
    0.15
    Activations Density 0.055%

    No Known Activations