© 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. 21478
    Prev
    Next
    INDEX
    Explanations

    URL routing and rewriting

    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
    裳
    -0.10
    ä¸Ĭä¸ĭ游
    -0.10
    湿润
    -0.09
    èĢĥåľº
    -0.09
    æłª
    -0.09
    ä¾Ľ
    -0.08
     bunk
    -0.08
    æ´ĩ
    -0.08
    èij³
    -0.08
    inos
    -0.08
    POSITIVE LOGITS
    åĪİ
    0.10
    åı·
    0.10
    FilterWhere
    0.09
    atedRoute
    0.09
    æĸĹ
    0.09
    ("/{
    0.09
    æİ©
    0.08
    .pathname
    0.08
    .masks
    0.08
    (Route
    0.08
    Activations Density 0.420%

    No Known Activations