© 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. 17206
    Prev
    Next
    INDEX
    Explanations

    maximum sustained winds, strengthened into, ahead of

    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
    严éĩįå½±åĵį
    -0.09
    漫éķ¿
    -0.08
     Alto
    -0.08
    é¢ĦèѦ
    -0.08
    æĶ¿åºľ
    -0.08
    æĿ¥ä¸´
    -0.08
    æķħ乡
    -0.08
    é¹ħ
    -0.08
    tap
    -0.08
    æIJºå¸¦
    -0.08
    POSITIVE LOGITS
    strup
    0.09
    é¦Ļæ°Ķ
    0.09
    ointment
    0.09
    LÄ°
    0.09
     Haram
    0.09
    åıij表
    0.08
    åĢ©
    0.08
    oron
    0.08
     swims
    0.08
    fono
    0.08
    Activations Density 0.040%

    No Known Activations