© 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. 52711
    Prev
    Next
    INDEX
    Explanations

    edited as, governed by, Force SF

    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
    alin
    -0.09
    oz
    -0.09
    getFile
    -0.08
    éĽī
    -0.08
    æĪļ
    -0.08
     kì
    -0.08
    æİĢ
    -0.08
    忱
    -0.08
     Gilles
    -0.08
    .EventHandler
    -0.08
    POSITIVE LOGITS
     khợi
    0.10
    ä¸ĢæĹı
    0.09
    åİŁåĪĽ
    0.08
    没æĶ¶
    0.08
    restart
    0.08
    bone
    0.08
    æľ¬çĿĢ
    0.08
    丰
    0.08
    åĶ·
    0.08
    èĬĤ约
    0.08
    Activations Density 0.003%

    No Known Activations