© 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. 22333
    Prev
    Next
    INDEX
    Explanations

    Swan, crane, birds

    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
    ters
    -0.09
    æĸ¯åŁº
    -0.09
    ation
    -0.09
    禺
    -0.08
    红楼
    -0.08
    ÑıÑģ
    -0.08
    naire
    -0.08
    éĩijå±±
    -0.08
    stin
    -0.08
    åłĨæĶ¾
    -0.08
    POSITIVE LOGITS
     Rosenstein
    0.10
    åĩ«
    0.10
    shore
    0.09
    alysis
    0.09
     scape
    0.08
    manship
    0.08
    ritic
    0.08
    禧
    0.08
    岬
    0.08
    æľµ
    0.08
    Activations Density 0.012%

    No Known Activations