© 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. 27532
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    lit
    -0.09
    çĽijäºĭ
    -0.08
    çļĦåIJĦ项
    -0.08
    ä½ľä¸ºä¸Ģç§į
    -0.08
    æ±ĩ
    -0.07
    ëĤł
    -0.07
    à¸ķรา
    -0.07
    long
    -0.07
    åħĭèݱ
    -0.07
     Neutral
    -0.07
    POSITIVE LOGITS
    åŀ¢
    0.11
    ä»Ģä¹ĪåİŁåĽł
    0.11
    ç»Ļä½łä»¬
    0.10
    åĪį
    0.10
    ız
    0.10
    è¯ļæĦı
    0.10
    UTO
    0.10
    è¿Ľä¸ĢæŃ¥
    0.09
    TRIES
    0.09
    æĤ¦
    0.09
    Activations Density 0.108%

    No Known Activations