© 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. 50218
    Prev
    Next
    INDEX
    Explanations

    expand, report, or elaborate on

    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
    .Place
    -0.08
    ä¸Ģéģĵ
    -0.08
    handler
    -0.08
    æľºåĬ¨
    -0.08
    å¼Ģæ°´
    -0.08
     Hunt
    -0.08
    ä½ķåĨµ
    -0.08
    å¯Įæ°ij
    -0.08
    mie
    -0.08
    urf
    -0.08
    POSITIVE LOGITS
     upon
    0.17
     on
    0.15
     trên
    0.13
     عÙĦÙĬÙĩ
    0.13
     عÙĦÙĬÙĥ
    0.13
     عÙĦÙī
    0.13
     عÙĦÙĬÙĩا
    0.12
     عÙĦÙĬÙĩÙħ
    0.12
     onto
    0.12
     darauf
    0.12
    Activations Density 0.075%

    No Known Activations