© 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. 18575
    Prev
    Next
    INDEX
    Explanations

    Apple product names

    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
     Barton
    -0.09
    è¡Įç¨ĭ
    -0.09
    åĺŁ
    -0.09
    zell
    -0.08
     WHETHER
    -0.08
    Mutable
    -0.08
    amar
    -0.08
     во
    -0.08
    ä¸ŃåĽ½äººæ°ij
    -0.08
    ive
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ人éĥ½
    0.09
    .Merge
    0.08
    RefCount
    0.08
    olis
    0.08
    åºIJ
    0.08
    ãģ«ãģªãģ£ãģ¦
    0.08
     Mayer
    0.08
     знаÑĤÑĮ
    0.08
    ãģĩ
    0.08
    ä¸į幸
    0.08
    Activations Density 0.002%

    No Known Activations