© 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. 23068
    Prev
    Next
    INDEX
    Explanations

    musical theatre productions

    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
    追赶
    -0.10
    ennon
    -0.10
    _ui
    -0.09
    è·Łè¸ª
    -0.09
     ÑĢазвива
    -0.09
    åĨ·éĿĻ
    -0.09
     Rating
    -0.09
    stell
    -0.08
     нед
    -0.08
    asse
    -0.08
    POSITIVE LOGITS
    éŃħåĬĽ
    0.08
    åĪ©çĽĬ
    0.08
    erald
    0.08
    æħĿ
    0.08
    inee
    0.08
     Äijá»īnh
    0.08
    èģĺçĶ¨
    0.08
    è¸ŀ
    0.08
    æĽĿ
    0.08
    æľīçļĦ人
    0.08
    Activations Density 0.009%

    No Known Activations