© 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. 52793
    Prev
    Next
    INDEX
    Explanations

    dining and food establishments

    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
    çĶľçĶľ
    -0.10
    æĿ¯
    -0.09
    .urlencoded
    -0.09
    åıĤ
    -0.09
    bilder
    -0.09
    ãģįãģ£ãģ¨
    -0.09
    享
    -0.08
    京津
    -0.08
     Bilder
    -0.08
    é¢Ģ
    -0.08
    POSITIVE LOGITS
    碰
    0.09
    Instagram
    0.08
    éĩįå¿ĥ
    0.08
    æݨéĢģ
    0.08
     Instagram
    0.08
    ä¸Ĭè°ĥ
    0.08
     долж
    0.08
    æİ·
    0.08
     Fucking
    0.08
    æķijåĬ©
    0.08
    Activations Density 0.085%

    No Known Activations