© 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. 32308
    Prev
    Next
    INDEX
    Explanations

    lavender; avonne; lavrijsen

    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
    cta
    -0.09
    æ°ª
    -0.09
     Lam
    -0.09
    足
    -0.08
    ç®Ĺæĺ¯
    -0.08
    iment
    -0.08
    gu
    -0.08
     Atom
    -0.08
    roi
    -0.08
    (PC
    -0.08
    POSITIVE LOGITS
    ä¹ĭéĻħ
    0.09
    PRI
    0.09
    æĪIJç«ĭäºĨ
    0.09
    å®īå®ļ
    0.09
     Stable
    0.09
    éĻ¢éķ¿
    0.08
    驼
    0.08
    åĩºçİ°äºĨ
    0.08
    æī©æķ£
    0.08
    顺åĪ©
    0.08
    Activations Density 0.012%

    No Known Activations