© 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. 27508
    Prev
    Next
    INDEX
    Explanations

    customer service representative

    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
    æĭ¥
    -0.10
    ä¹ĭæĪĺ
    -0.10
    笥
    -0.10
    cord
    -0.10
    èļ¤
    -0.10
    tÃŃ
    -0.10
    uem
    -0.10
     BÃł
    -0.09
    ionale
    -0.09
    ä¹ĭæĹħ
    -0.09
    POSITIVE LOGITS
    0
    0.09
    åijĺ
    0.09
    åĵ¡
    0.08
    ukes
    0.08
    åı°è¯į
    0.08
    åij
    0.07
    pper
    0.07
    ru
    0.07
    æĹ·
    0.07
     vested
    0.07
    Activations Density 0.019%

    No Known Activations