© 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. 18375
    Prev
    Next
    INDEX
    Explanations

    cost reduction and improvement

    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
    onis
    -0.09
    å®ķ
    -0.09
    åľ¨æł¡
    -0.09
    istar
    -0.09
    èłĸ
    -0.09
    ä¸įæĺĵ
    -0.08
    çĤ¹å¤ļ
    -0.08
    计
    -0.08
    çĶ³
    -0.08
    è¨Ī
    -0.08
    POSITIVE LOGITS
    æĪIJçĨŁ
    0.10
    è´¨
    0.09
    [vi
    0.09
    ä»·éĴ±
    0.09
     costs
    0.09
    nown
    0.09
    ç§ijæĬĢè¿ĽæŃ¥
    0.09
    é©´
    0.09
    ç»Ħç»ĩé¢Ĩ导
    0.08
    楸
    0.08
    Activations Density 0.074%

    No Known Activations