© 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. 39021
    Prev
    Next
    INDEX
    Explanations

    locations and dates

    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
    ä¿©
    -0.11
    æĸ¯é¡¿
    -0.10
    åĴĮæĬĢæľ¯
    -0.10
    è¡°
    -0.09
    æĪijçļĦå¿ĥ
    -0.09
    æĺŁåº§
    -0.09
    åħ«å¹´
    -0.09
    주ìĿĺ
    -0.09
    åİĨåı²æĤłä¹ħ
    -0.09
    åĽŀå¿Ĩ
    -0.09
    POSITIVE LOGITS
    رÙĪÙħ
    0.08
    à¹ģà¸ŀ
    0.08
    ResponseStatus
    0.08
    足
    0.08
     \"
    0.07
    快讯
    0.07
    HAVE
    0.07
    /jpeg
    0.07
    ÙĦد
    0.07
    lek
    0.07
    Activations Density 0.091%

    No Known Activations