© 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. 27501
    Prev
    Next
    INDEX
    Explanations

    tiny

    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
    大æĪĺ
    -0.10
    sic
    -0.10
    ses
    -0.10
    eds
    -0.10
    aten
    -0.09
    æĸ°åŁİ
    -0.09
    ayed
    -0.09
    -leaning
    -0.09
    voir
    -0.08
     ÑģлÑĥÑĩаÑı
    -0.08
    POSITIVE LOGITS
    /small
    0.14
    ê¹IJ
    0.11
    /tiny
    0.11
    té
    0.10
     amounts
    0.10
    ìĹĦ
    0.10
    ernet
    0.10
    è°Ł
    0.09
    atures
    0.09
    /simple
    0.09
    Activations Density 0.012%

    No Known Activations