© 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. 11359
    Prev
    Next
    INDEX
    Explanations

    books, plays, or named characters

    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
    åħ¬åĬ¡
    -0.10
    blocking
    -0.09
    ieber
    -0.09
    flare
    -0.09
    èħķ
    -0.09
     ка
    -0.09
    -thumbnails
    -0.08
    æĴŃæĶ¾
    -0.08
    erb
    -0.08
    åĬŀåħ¬åİħ
    -0.08
    POSITIVE LOGITS
    å°ı说
    0.12
    红楼梦
    0.12
    é²ģè¿ħ
    0.11
    å°ı說
    0.11
    æĬij
    0.10
    ç»ıåħ¸
    0.10
    åĽĬ
    0.09
    æĿİçĻ½
    0.09
    课æĸĩ
    0.09
    æ·±å±Ĥ
    0.09
    Activations Density 0.157%

    No Known Activations