© 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. 52996
    Prev
    Next
    INDEX
    Explanations

    enough followed by modifier

    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
    æŀľæłij
    -0.10
    å¸Ń
    -0.10
    outh
    -0.10
    uition
    -0.09
    èĢĮéĿŀ
    -0.09
    å®īå®ļ
    -0.09
    秸ç§Ĩ
    -0.08
    бин
    -0.08
    iding
    -0.08
    felt
    -0.08
    POSITIVE LOGITS
    cial
    0.09
     Gree
    0.09
    æ¾Ħ
    0.08
    yal
    0.08
     bö
    0.08
    æĺ¯ä¸Ģ件
    0.08
    _frm
    0.08
    åĪĹåĩº
    0.08
    _UNICODE
    0.08
    åįķçĭ¬
    0.08
    Activations Density 0.026%

    No Known Activations