© 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. 32616
    Prev
    Next
    INDEX
    Explanations

    Secret Fashion, Top Issue, Naomi Watts, World, Command line, meal effect

    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
     tack
    -0.12
    alan
    -0.10
    éĢļä¿Ĺ
    -0.10
    æIJª
    -0.09
    æĹłç¼ĺ
    -0.09
    çĢ¼
    -0.09
    诸èijĽ
    -0.09
    hci
    -0.09
    é¹Ĭ
    -0.09
    çī¯
    -0.08
    POSITIVE LOGITS
    REE
    0.10
    模çī¹
    0.10
    ç´ł
    0.09
    è£ĻåŃIJ
    0.09
    cargo
    0.09
     imper
    0.08
    rift
    0.08
    æīĭä¸ŃçļĦ
    0.08
    巨人
    0.08
     Revel
    0.08
    Activations Density 0.016%

    No Known Activations