© 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. 27790
    Prev
    Next
    INDEX
    Explanations

    return on investment

    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
    èĢĮåIJİ
    -0.11
    æ·¡åĮĸ
    -0.10
    é¢Ĥ
    -0.10
    çijĹ
    -0.09
    éĹ´æİ¥
    -0.09
    ä¸ĬæĬ¥
    -0.08
    èĩ´
    -0.08
    æ³ķåĪ¶
    -0.08
    å¤ľæĻļ
    -0.08
    vc
    -0.08
    POSITIVE LOGITS
    åĽŀæĬ¥
    0.12
    åŃĸ
    0.10
    ä¸įé«ĺ
    0.10
    uard
    0.09
    æĺİçıł
    0.09
    íĽĪ
    0.09
    ãģ©ãģĵãĤį
    0.08
     Orig
    0.08
    _IDX
    0.08
    åķĦ
    0.08
    Activations Density 0.007%

    No Known Activations