© 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. 8713
    Prev
    Next
    INDEX
    Explanations

    last known, seen, or updated

    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
    åįļ主
    -0.10
    gon
    -0.10
    çĽĬ
    -0.09
    Terr
    -0.09
    æĿ¥äºĨ
    -0.08
    æĹ¢èĥ½
    -0.08
    çŀİ
    -0.08
    鼩
    -0.08
    adv
    -0.08
    GH
    -0.08
    POSITIVE LOGITS
    为æŃ¢
    0.10
    adem
    0.10
    åĩºæīĭ
    0.09
    æī¿
    0.09
    æ´Ľ
    0.08
    èħł
    0.08
    éĻ£
    0.08
    ëįĺ
    0.08
    æĵ¦æĭŃ
    0.08
    lang
    0.08
    Activations Density 0.032%

    No Known Activations