© 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. 57512
    Prev
    Next
    INDEX
    Explanations

    event details and 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
    éĩĬ
    -0.09
    宥
    -0.08
    è·¨è¶Ĭå¼ı
    -0.08
    عاÙĦ
    -0.08
    odyn
    -0.08
    âľİ
    -0.08
    主ç¼ĸ
    -0.08
    ç¼ĸåĨĻ
    -0.08
    滢
    -0.08
    .rmi
    -0.08
    POSITIVE LOGITS
     меÑĢопÑĢи
    0.11
     меÑĢопÑĢиÑıÑĤиÑı
    0.11
    举è¡ĮçļĦ
    0.10
    åľ°çĤ¹
    0.10
    .event
    0.10
     event
    0.09
    äºĭ件
    0.09
    室å¤ĸ
    0.09
    åħµåĻ¨
    0.09
    åľºæīĢ
    0.09
    Activations Density 0.045%

    No Known Activations