© 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. 38710
    Prev
    Next
    INDEX
    Explanations

    registered engineers

    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°ĩ
    -0.09
    rette
    -0.08
    æ¦ľ
    -0.08
    延ç»Ń
    -0.08
    æıIJæĹ©
    -0.08
    kil
    -0.08
    éĴ¦
    -0.08
    å
    -0.08
    enger
    -0.08
    个å°ı
    -0.08
    POSITIVE LOGITS
    èŀºæĹĭ
    0.09
    æ¢ĵ
    0.08
    æѦåĬŁ
    0.08
    imbus
    0.08
    /vendor
    0.08
    lessly
    0.08
     Nie
    0.08
    .dist
    0.08
    æģ©æĸ½
    0.08
    汧
    0.08
    Activations Density 0.256%

    No Known Activations