© 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. 19270
    Prev
    Next
    INDEX
    Explanations

    places like Pitt and Pittsburgh

    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
    hoot
    -0.09
    带头人
    -0.09
    erve
    -0.09
    .skin
    -0.08
    eric
    -0.08
    erves
    -0.08
    á»Ńa
    -0.08
    دÙĤ
    -0.08
    æŃī
    -0.08
    ä¼ļå¼ķèµ·
    -0.08
    POSITIVE LOGITS
    iales
    0.10
    ford
    0.10
    zed
    0.08
    lessness
    0.08
     во
    0.08
    ety
    0.08
    æīĢä»¥åľ¨
    0.08
    stock
    0.08
    为空
    0.08
    ston
    0.08
    Activations Density 0.003%

    No Known Activations