© 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. 2867
    Prev
    Next
    INDEX
    Explanations

    retail stores and pharmacies

    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
    psc
    -0.10
    emaker
    -0.10
    ifax
    -0.09
     Provincial
    -0.09
    -cancel
    -0.09
     Fraser
    -0.09
    é£İæīĩ
    -0.08
    ataka
    -0.08
    .override
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
    ickness
    0.09
    åĩºåħ¥
    0.09
    éļıå¤Ħ
    0.08
    åĨħå¤ĸ
    0.08
    argo
    0.08
    ãĢģãĢĮ
    0.08
     веÑģ
    0.08
    è··
    0.08
    éĺŁ
    0.08
    å·§å¦Ļ
    0.08
    Activations Density 0.004%

    No Known Activations