© 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. 10655
    Prev
    Next
    INDEX
    Explanations

    suffragan or suffocation

    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
    åįģæĿ¡
    -0.11
    笳
    -0.10
    æĹłå¿§
    -0.10
    anship
    -0.10
    forc
    -0.09
    лин
    -0.09
    éģ½
    -0.09
    ä¸īæĿ¡
    -0.09
    ãĥ¬ãĥĵ
    -0.09
    常è§ģçļĦ
    -0.09
    POSITIVE LOGITS
    hen
    0.09
     Sandwich
    0.09
    iber
    0.09
    æľīçļĦ
    0.09
    åİĭ
    0.09
    iem
    0.08
    hi
    0.08
    emann
    0.08
    mers
    0.08
    ãģıãģłãģķãģĦ
    0.08
    Activations Density 0.003%

    No Known Activations