© 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. 10858
    Prev
    Next
    INDEX
    Explanations

    street addresses

    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
    çĤ¹æ»´
    -0.11
    åĴĮåıijå±ķ
    -0.10
    åľ¨è¿Ļç§į
    -0.09
    æĦŁäºº
    -0.09
    èĢ»
    -0.09
    bour
    -0.09
    è¡Ķ
    -0.08
    èIJ¥éĢłèī¯å¥½
    -0.08
    marine
    -0.08
    èģĮ
    -0.08
    POSITIVE LOGITS
    forth
    0.09
     Parkway
    0.08
    (SE
    0.08
    é«ĺæĸ°
    0.08
    @author
    0.08
    ä¾ĥ
    0.08
    .gwt
    0.08
    seo
    0.08
    chan
    0.08
    èĩªä¸»åĪĽæĸ°
    0.08
    Activations Density 0.073%

    No Known Activations