© 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. 49063
    Prev
    Next
    INDEX
    Explanations

    increase or addition

    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
    éĦĻ
    -0.10
    .sd
    -0.10
    å¾Ī好çļĦ
    -0.10
    -go
    -0.10
    äºĶ大
    -0.09
    车主
    -0.09
    åķĨåĬ¡
    -0.09
    å¾Īå·®
    -0.09
    åĨįä¹Łæ²¡æľī
    -0.09
     Äijợi
    -0.09
    POSITIVE LOGITS
    带æĿ¥çļĦ
    0.10
    é¡¿
    0.09
    åīįèĢħ
    0.09
    iveness
    0.08
    æīĢ带æĿ¥çļĦ
    0.08
     traj
    0.08
    ä½ĵçİ°åľ¨
    0.08
    ulle
    0.08
     Hur
    0.08
    çªĿ
    0.08
    Activations Density 0.076%

    No Known Activations