© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36240
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ç´
    -0.09
    mÄ±ÅŁ
    -0.09
    èĬĴ
    -0.09
    лож
    -0.08
    çŃ¹éĽĨ
    -0.08
    æĮģãģ¡
    -0.08
    声
    -0.08
    .mozilla
    -0.08
    edList
    -0.08
     аналог
    -0.08
    POSITIVE LOGITS
    äºĮåŃĹ
    0.13
    utton
    0.11
    è¿Ļ个è¯į
    0.11
    æľªæĿ¥åıijå±ķ
    0.10
    plate
    0.09
    plates
    0.08
    è¿Ļ个åIJįåŃĹ
    0.08
    UTTON
    0.08
    ifice
    0.08
    здание
    0.08
    Activations Density 0.205%

    No Known Activations