© 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. 30445
    Prev
    Next
    INDEX
    Explanations

    name suffixes and endings

    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
    ago
    -0.09
    ä½³
    -0.08
    erval
    -0.08
     chief
    -0.08
    åºĨ
    -0.08
    endl
    -0.08
    港澳
    -0.08
    ä¸Ģä½ĵ
    -0.08
    Grammar
    -0.08
    è£ķ
    -0.08
    POSITIVE LOGITS
    人æĿĥ
    0.10
    ä¸įæĺ¯å¾Ī
    0.09
    åĬ²
    0.09
    å¿ĥæĢĿ
    0.09
    jing
    0.09
    对æĸ¹
    0.09
    ç«ĸ
    0.08
    橹
    0.08
    åĽ´ç»ķ
    0.08
    讵
    0.08
    Activations Density 0.225%

    No Known Activations