© 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. 23621
    Prev
    Next
    INDEX
    Explanations

    free download, streaming, ads, price

    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
     vess
    -0.09
    离åİ»
    -0.09
    æĦĪåıij
    -0.08
    ä¸Ģå°ı
    -0.08
    ä¸įç®Ĺ
    -0.08
    ä¸Ģé¡¿
    -0.08
    åıĺå¹»
    -0.08
    糧
    -0.08
    èĿ¶
    -0.08
    .deck
    -0.08
    POSITIVE LOGITS
     Gund
    0.11
    mens
    0.10
    ä¸ĸçķĮçļĦ
    0.09
    æıIJä¾Ľ
    0.09
     Lob
    0.09
    arde
    0.08
     lud
    0.08
    æįº
    0.08
    -www
    0.08
    åĨįä¹Łæ²¡æľī
    0.08
    Activations Density 0.157%

    No Known Activations