© 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. 22259
    Prev
    Next
    INDEX
    Explanations

    weather descriptions

    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
    çĤ¸å¼¹
    -0.10
    æľįä»İ
    -0.10
    碰
    -0.09
    æĮij
    -0.08
     spre
    -0.08
    çļĦ表çİ°
    -0.08
    åį±
    -0.08
    è¸ī
    -0.08
    eri
    -0.08
    åīįè¾Ī
    -0.08
    POSITIVE LOGITS
    çĤİçĥŃ
    0.10
    æ°Ķ温
    0.10
    温åĴĮ
    0.10
    å¯ĴåĨ·
    0.10
    çļĦåľ°æĸ¹
    0.09
    çݯå¢ĥä¸Ń
    0.09
     windy
    0.09
    温度
    0.09
    NewItem
    0.09
     вокÑĢÑĥг
    0.09
    Activations Density 0.064%

    No Known Activations