© 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. 27711
    Prev
    Next
    INDEX
    Explanations

    superior quality and service

    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
    äºķ
    -0.09
    lds
    -0.09
    igers
    -0.08
    alar
    -0.08
    æ°ĹãģĮ
    -0.08
    å¾Ī大çļĦ
    -0.08
    ç§ijåѦéĻ¢
    -0.08
    åĴİ
    -0.08
    èĢģèĻİ
    -0.08
    utures
    -0.08
    POSITIVE LOGITS
    æķĽ
    0.10
    ä»ĸå°±
    0.10
    æīĢ以ä»ĸ
    0.09
    éĻ¤æѤ
    0.09
    æ³Ħ
    0.09
    elier
    0.09
    pez
    0.09
    æĢ§ä»·
    0.09
    adera
    0.09
    ort
    0.09
    Activations Density 0.037%

    No Known Activations