© 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. 27126
    Prev
    Next
    INDEX
    Explanations

    type or types

    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
    æµĶ
    -0.10
    榧
    -0.09
    assen
    -0.09
    isto
    -0.08
    ront
    -0.08
    楼çĽĺ
    -0.08
    åIJĮç±»
    -0.08
    èµİ
    -0.08
    梦幻
    -0.08
    æĭ³å¤´
    -0.08
    POSITIVE LOGITS
     magg
    0.09
    ä¸įå½ĵ
    0.09
    åħ·
    0.08
    鹿
    0.08
    åľ°éľĩ
    0.08
    /name
    0.08
    举
    0.08
    çijĢ
    0.08
    getSingleton
    0.08
    chet
    0.08
    Activations Density 0.308%

    No Known Activations