© 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. 1809
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms

    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
    ç§ijæĬĢåĽŃ
    -0.08
    åij¤
    -0.08
    渺
    -0.08
     Blackburn
    -0.08
    buyer
    -0.08
    SCII
    -0.08
    缸äºĴ
    -0.08
    楼ä¸ĭ
    -0.08
    licken
    -0.07
    æĵ¬
    -0.07
    POSITIVE LOGITS
    æijĬ
    0.09
    å°¤
    0.08
    ULATOR
    0.08
    ä¸Ńå¼ı
    0.08
     unm
    0.08
    éģĩåĪ°äºĨ
    0.08
    ำ
    0.08
     unl
    0.08
    cur
    0.08
    横
    0.08
    Activations Density 0.133%

    No Known Activations