© 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. 61733
    Prev
    Next
    INDEX
    Explanations

    dedicated to

    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
    atters
    -0.09
    Å¡t
    -0.09
    stad
    -0.09
     Gef
    -0.09
    im
    -0.09
    boat
    -0.08
    net
    -0.08
    æ·»
    -0.08
    ôn
    -0.08
    ored
    -0.08
    POSITIVE LOGITS
    edly
    0.11
    ../../../
    0.11
    ми
    0.10
    ãģĤãĤĭç¨ĭ度
    0.10
    ÑĢиÑģ
    0.10
    rror
    0.09
    ubre
    0.09
    stration
    0.09
    æĢ§å¼º
    0.09
    ا
    0.09
    Activations Density 0.012%

    No Known Activations