© 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. 35420
    Prev
    Next
    INDEX
    Explanations

    ste endings

    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
    åŃIJéĩĮ
    -0.10
    stellung
    -0.10
    itecture
    -0.10
    nette
    -0.10
    تب
    -0.10
    ãģĦãĤĭ
    -0.09
    æ»ĵ
    -0.09
    ampa
    -0.09
    ¡
    -0.09
    rud
    -0.09
    POSITIVE LOGITS
    stakes
    0.10
    pped
    0.10
    iola
    0.09
    pping
    0.09
    uve
    0.09
    inar
    0.09
    Äĩ
    0.09
    å°ıå¿ĥ
    0.09
    åĢij
    0.09
    zano
    0.09
    Activations Density 0.019%

    No Known Activations