© 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. 52731
    Prev
    Next
    INDEX
    Explanations

    evening

    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
    çľ¼çļ®
    -0.09
    owanie
    -0.08
    itive
    -0.08
    ı
    -0.08
    èīĩ
    -0.08
    çľ¼æ³ª
    -0.08
    icip
    -0.08
     же
    -0.08
    elling
    -0.08
    elsen
    -0.08
    POSITIVE LOGITS
    uate
    0.11
     dÃłng
    0.10
    ixo
    0.10
    รà¸Ńย
    0.10
    ãĢħ
    0.10
    roman
    0.10
    uation
    0.10
    ะ
    0.10
    ancies
    0.09
    ë¡ł
    0.09
    Activations Density 0.006%

    No Known Activations