© 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. 23412
    Prev
    Next
    INDEX
    Explanations

    logical operators and symbols

    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
    ora
    -0.09
    çĿĢæīĭ
    -0.09
    club
    -0.08
    -0.08
    weis
    -0.08
    inez
    -0.08
    åİĦ
    -0.08
     DC
    -0.07
     Sofia
    -0.07
    ×ķ×ļ
    -0.07
    POSITIVE LOGITS
    æ·ĭ
    0.10
    vanced
    0.09
    讳
    0.09
    æĽĻ
    0.09
    cpy
    0.09
    ination
    0.09
    argar
    0.09
    rack
    0.09
    æľīæľŁ
    0.08
    aida
    0.08
    Activations Density 0.033%

    No Known Activations