© 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. 2534
    Prev
    Next
    INDEX
    Explanations

    from other

    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
    ä»£æĽ¿
    -0.10
    åIJĮ缣
    -0.09
    æİ¥éĢģ
    -0.09
    hl
    -0.09
    æī©åħħ
    -0.09
    è¿ĺè®°å¾Ĺ
    -0.08
    åĬ©
    -0.08
     uncomp
    -0.08
    층
    -0.08
    Invoker
    -0.08
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.14
     other
    0.13
    åħ¶ä»ĸ
    0.12
     autres
    0.12
    å¤ĸçķĮ
    0.11
    åħ¶ä»ĸçļĦ
    0.11
    åħ¶å®ĥ
    0.11
    ä¸ĢèĪ¬çļĦ
    0.11
     demás
    0.11
    åħ¶ä»ĸ人
    0.10
    Activations Density 0.074%

    No Known Activations