© 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. 17094
    Prev
    Next
    INDEX
    Explanations

    inside a location

    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
    éĻĶ
    -0.10
    åľ¨æѤ
    -0.10
    ç¢į
    -0.10
    åľ¨æĪij
    -0.09
    åľ¨è¿ĻéĩĮ
    -0.09
    orning
    -0.09
    onaut
    -0.09
    åľ¨éĤ£éĩĮ
    -0.09
    èĩ³äºİ
    -0.09
    ings
    -0.09
    POSITIVE LOGITS
    /out
    0.13
    -sama
    0.09
    /on
    0.09
     него
    0.09
    åIJĦèĩªçļĦ
    0.09
    æĸ°ä¸Ģè½®
    0.08
    ensively
    0.08
     ÑģебÑı
    0.08
    人们çļĦ
    0.08
    Ùħا
    0.08
    Activations Density 0.020%

    No Known Activations