© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37544
    Prev
    Next
    INDEX
    Explanations

    years of experience

    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
     доÑģÑĤиж
    -0.10
    åįģäºĮäºĶ
    -0.10
    个å¤ļ
    -0.09
    å½ĵä»Ĭ
    -0.09
    forge
    -0.09
    ä½ķæŶ
    -0.09
    è¿Ļç¯ĩæĸĩç«ł
    -0.09
    å°½æĹ©
    -0.09
    æľªæĿ¥çļĦ
    -0.08
    æĽ´åħ·
    -0.08
    POSITIVE LOGITS
    gers
    0.09
    å¨ĺ
    0.08
     Garner
    0.08
    ç²ij
    0.08
    .Console
    0.08
    æĹĹèĪ°
    0.08
    dif
    0.08
    eman
    0.08
    ç«Ļ
    0.08
    stant
    0.08
    Activations Density 0.015%

    No Known Activations