© 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. 35588
    Prev
    Next
    INDEX
    Explanations

    purpose or reason

    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
    漪
    -0.09
    /from
    -0.09
    alion
    -0.09
    mani
    -0.08
    ä¸Ģè¾Ĩ
    -0.08
     Peel
    -0.08
    å½Ģ
    -0.08
    paginator
    -0.08
    éĢģåİ»
    -0.08
    llum
    -0.08
    POSITIVE LOGITS
    æ¼ı
    0.12
    å¾ķ
    0.10
    çīµ
    0.10
     leaking
    0.09
    æ¶ĤæĬ¹
    0.09
     leak
    0.09
    è°ĵ
    0.08
    æ¥Ķ
    0.08
    å¤ĸæĿ¥
    0.08
    elize
    0.08
    Activations Density 0.148%

    No Known Activations