© 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. 4351
    Prev
    Next
    INDEX
    Explanations

    admirable efforts or 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
    äººæł¼
    -0.11
    bor
    -0.10
    itzer
    -0.09
    èĩªå®¶
    -0.09
    享åıĹ
    -0.09
    nier
    -0.09
    ç»ıæŁ¥
    -0.09
     Pend
    -0.09
    istani
    -0.08
    _mapped
    -0.08
    POSITIVE LOGITS
    åĭĩäºİ
    0.13
    åĭĩæ°Ķ
    0.12
    æķı
    0.10
    æľīä»·åĢ¼çļĦ
    0.10
     efforts
    0.10
    æľīä»·åĢ¼
    0.10
    æķ¢äºİ
    0.10
    éĶ²
    0.10
     courage
    0.09
    颦
    0.09
    Activations Density 0.045%

    No Known Activations