© 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. 54843
    Prev
    Next
    INDEX
    Explanations

    people magazine

    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
    è¯ĺ
    -0.09
    QueryBuilder
    -0.09
    ses
    -0.08
    åľ¨æĹ¥æľ¬
    -0.08
    ners
    -0.08
    èĨ³
    -0.08
     rib
    -0.08
    æģļ
    -0.07
    Rib
    -0.07
    åijĺ
    -0.07
    POSITIVE LOGITS
    ares
    0.09
    kop
    0.09
    awner
    0.09
    ersen
    0.09
    å®°
    0.09
    å¾Ģå¤ĸ
    0.09
    اÙħر
    0.09
    æµĶ
    0.09
    åħ±åĴĮåĽ½
    0.08
    enguin
    0.08
    Activations Density 0.040%

    No Known Activations