© 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. 11771
    Prev
    Next
    INDEX
    Explanations

    lend, lending, loans

    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
    engers
    -0.10
    ption
    -0.10
    enko
    -0.09
    teenth
    -0.09
    è°¨
    -0.09
    å®ģæĦ¿
    -0.09
    à®´
    -0.09
    ä¿Ń
    -0.09
    åīįæıIJæĺ¯
    -0.09
    å¿ĥåºķ
    -0.09
    POSITIVE LOGITS
    æĥľ
    0.10
    ings
    0.10
     ocas
    0.09
    ee
    0.09
    orsch
    0.09
    æģ¶å¿ĥ
    0.09
    stra
    0.08
     cred
    0.08
     bis
    0.08
    itures
    0.08
    Activations Density 0.011%

    No Known Activations