© 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. 9496
    Prev
    Next
    INDEX
    Explanations

    quote ending punctuation

    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
    cao
    -0.08
    atures
    -0.08
    pty
    -0.08
    åijIJ
    -0.08
    æľ¬é¢Ĩ
    -0.08
     Abb
    -0.08
    encies
    -0.08
    RTC
    -0.08
    cai
    -0.08
    ção
    -0.07
    POSITIVE LOGITS
    er
    0.19
    ãĥ£
    0.14
    Ùĩ
    0.12
    erk
    0.12
    ï¾ŀ
    0.11
    eron
    0.11
    ×ķ
    0.11
    ا
    0.11
    eria
    0.10
    zelf
    0.10
    Activations Density 0.034%

    No Known Activations