© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8148
    Prev
    Next
    INDEX
    Explanations

    German philosophers and thinkers

    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
    颦
    -0.09
    ç§įç§į
    -0.09
     Huff
    -0.09
    çºłæŃ£
    -0.09
    幡
    -0.08
     tiá»ĩn
    -0.08
    rer
    -0.08
    é¦ĸ
    -0.08
    JOB
    -0.08
    æµ·åĨħå¤ĸ
    -0.08
    POSITIVE LOGITS
    chal
    0.10
    äºĨä¸Ģåı¥
    0.09
    ian
    0.09
    æĿı
    0.08
    Slim
    0.08
    认为
    0.08
    uzzi
    0.08
    æĻļå¹´
    0.08
    çł
    0.08
    ish
    0.08
    Activations Density 0.079%

    No Known Activations