© 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. 4051
    Prev
    Next
    INDEX
    Explanations

    but, because

    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
    ä¸Ģé¢Ĺ
    -0.11
     chứ
    -0.10
    没éĶĻ
    -0.10
    htable
    -0.10
    èĢĮä¸Ķè¿ĺ
    -0.10
    è¿ĺæĺ¯å¾Ī
    -0.10
    ë§ŀ
    -0.10
    好åIJĹ
    -0.10
    ETING
    -0.09
    å¾Īå¤ļäºĭæĥħ
    -0.09
    POSITIVE LOGITS
    åįķçĭ¬
    0.11
    纳åħ¥
    0.10
    åı¦è¡Į
    0.10
     пока
    0.08
    olle
    0.08
    åĪĹåħ¥
    0.08
    çĶľ
    0.08
    åľ¨è¿Ļ个
    0.08
     fro
    0.08
    æĺĻ
    0.08
    Activations Density 0.100%

    No Known Activations