© 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. 62377
    Prev
    Next
    INDEX
    Explanations

    long after

    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
    åħĪæĬĬ
    -0.09
    angen
    -0.09
    æľīéĻIJ
    -0.09
    åŃĹ
    -0.09
    afia
    -0.08
    лÑİд
    -0.08
    ’Ãł
    -0.08
    ONA
    -0.08
    æ·±èĢķ
    -0.08
    ãģ¡
    -0.08
    POSITIVE LOGITS
    éķ¿éķ¿çļĦ
    0.12
    漫éķ¿çļĦ
    0.10
    è¾ĥéķ¿
    0.10
    ç¼ĵæħ¢
    0.09
    (er
    0.09
    è·ĭ
    0.09
    漫éķ¿
    0.09
    ened
    0.09
    ish
    0.08
    çłĶ究表æĺİ
    0.08
    Activations Density 0.029%

    No Known Activations