© 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. 61876
    Prev
    Next
    INDEX
    Explanations

    organizations and entities

    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
    wap
    -0.09
    æĭį
    -0.09
    ина
    -0.09
    æıŃ
    -0.08
    cfg
    -0.08
    æĴĤ
    -0.08
     camp
    -0.08
    åīįæıIJ
    -0.08
    (skip
    -0.08
    è
    -0.08
    POSITIVE LOGITS
    å®ĹæŨ
    0.10
    éĢīåĿĢ
    0.10
    èij¡
    0.10
    å®Įåħ¨æĺ¯
    0.10
    _RCC
    0.10
    æĪIJç«ĭ
    0.10
    æĪIJç«ĭäºİ
    0.09
     znalaz
    0.09
    æĪIJåijĺ
    0.09
    èĩªçĦ¶ä¿ĿæĬ¤
    0.09
    Activations Density 0.175%

    No Known Activations