© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38519
    Prev
    Next
    INDEX
    Explanations

    HTC smartphone, Lenovo, ASUS models

    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
    éĩįéĩį
    -0.10
    ollen
    -0.09
     Bos
    -0.09
    éĤ»
    -0.09
    yor
    -0.08
    交代
    -0.08
    Ingredients
    -0.08
    é¢Ķ
    -0.08
    ingo
    -0.08
    .Formatter
    -0.08
    POSITIVE LOGITS
    ä¸ļ
    0.08
    shoot
    0.08
    NSE
    0.08
    Ñħож
    0.08
    履约
    0.08
     SHA
    0.08
    -owner
    0.08
    ¥
    0.08
    -watch
    0.07
    -eye
    0.07
    Activations Density 0.003%

    No Known Activations