© 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. 19316
    Prev
    Next
    INDEX
    Explanations

    origin descriptors like -born, -based, -old

    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
    éĤ£ç§į
    -0.11
    çļĦéĤ£ç§į
    -0.10
    éĤ£æł·çļĦ
    -0.10
    ieber
    -0.08
    è¿Ļè¾¹
    -0.08
    åĺ´
    -0.08
    åħ¶ä»ĸçļĦ
    -0.08
    硬åĮĸ
    -0.08
    éĤ£ä¸ªæŶåĢĻ
    -0.08
    unu
    -0.08
    POSITIVE LOGITS
    ç²¾çģµ
    0.10
    ç¾Ĭæ¯Ľ
    0.10
    irs
    0.09
    estr
    0.09
    åĪĨå±Ģ
    0.09
    ä»ħ次äºİ
    0.09
     Damon
    0.09
    eli
    0.09
    iasco
    0.08
    ä¸Ģç»ı
    0.08
    Activations Density 0.268%

    No Known Activations