© 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. 1471
    Prev
    Next
    INDEX
    Explanations

    TV personalities and shows

    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¸ĵä¸ļåĮĸ
    -0.08
    è¹ģ
    -0.08
    _almost
    -0.08
     ind
    -0.08
    _already
    -0.08
    太é«ĺ
    -0.08
     knees
    -0.08
    .spy
    -0.08
    éĤ£æ¬¡
    -0.08
    å®ļä»·
    -0.08
    POSITIVE LOGITS
    éĤĢ
    0.10
    ãĥ¯
    0.08
    jah
    0.08
    reed
    0.08
    аÑĢам
    0.08
    _PHP
    0.08
    æ°´æĻ¶
    0.08
    èİ«æĸ¯
    0.08
    带åĬ¨
    0.08
    æĻŁ
    0.08
    Activations Density 0.018%

    No Known Activations