© 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. 7753
    Prev
    Next
    INDEX
    Explanations

    spaghetti or ziti with

    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
    éĢĿ
    -0.10
    vents
    -0.09
    çĿ«æ¯Ľ
    -0.09
     Gratuit
    -0.09
     Cath
    -0.09
    ryo
    -0.09
    ä¸įåı¯æĢĿè®®
    -0.09
    ines
    -0.08
    uds
    -0.08
    æŃ»èĢħ
    -0.08
    POSITIVE LOGITS
    oge
    0.10
    èį¦
    0.10
    ç´§çĽ¯
    0.09
    ä¸Ģè¶Ł
    0.09
    çĢijå¸ĥ
    0.09
    azzi
    0.09
    ä¸į代表
    0.09
    å¾Ĺ好
    0.09
    俯
    0.09
    æ·Ģç²ī
    0.08
    Activations Density 0.003%

    No Known Activations