© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9365
    Prev
    Next
    INDEX
    Explanations

    steroids and drugs

    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
    强è¡Į
    -0.09
    LE
    -0.09
    ä»»ä½ķå½¢å¼ı
    -0.08
    ibrate
    -0.08
    .Void
    -0.08
    å½
    -0.08
    ä¸įè¦ģåĨį
    -0.08
    éĥ½åĸľæ¬¢
    -0.08
     surre
    -0.08
    æ²Ļé¾Ļ
    -0.08
    POSITIVE LOGITS
    沸
    0.09
    åIJĪæ³ķ
    0.09
    жи
    0.08
    çĦļ
    0.08
    imax
    0.08
    иÑĩеÑģкое
    0.08
    èIJĭ
    0.08
    æĶ¯éħį
    0.08
    oho
    0.08
    izzy
    0.08
    Activations Density 0.022%

    No Known Activations