© 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. 17741
    Prev
    Next
    INDEX
    Explanations

    autoconf, autotools, configure scripts

    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
    èĥĸ
    -0.09
    æµ¥
    -0.09
    ä¿¡è´·
    -0.09
    alytics
    -0.08
     shotgun
    -0.08
    æĺ¥èĬĤæľŁéĹ´
    -0.08
     fı
    -0.08
    è´£ç¼ĸ
    -0.08
    æĸľ
    -0.08
    溢
    -0.08
    POSITIVE LOGITS
    AVA
    0.09
    åIJ¸
    0.08
    edar
    0.08
     systemd
    0.08
    çł»
    0.08
     GENERATED
    0.08
    æݥ触åĪ°
    0.08
     Evel
    0.08
    emas
    0.08
    -power
    0.08
    Activations Density 0.240%

    No Known Activations