© 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. 1468
    Prev
    Next
    INDEX
    Explanations

    job hunt

    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
    å¡ij
    -0.11
    æľįåĬ¡èĥ½åĬĽ
    -0.10
    éªĩ
    -0.09
    å¡Į
    -0.09
    abinet
    -0.09
    æĸ°éĹ»è®°èĢħ
    -0.09
    èĢģ人家
    -0.08
     Slee
    -0.08
    obe
    -0.08
    ÙħاÙħ
    -0.08
    POSITIVE LOGITS
    æĮīæŶ
    0.09
    人家
    0.09
    æ®ļ
    0.09
    ãģ¬
    0.08
    ETERS
    0.08
    å©Ģ
    0.08
     invo
    0.08
    zeich
    0.08
    æĹħ
    0.07
    æ¡Ī
    0.07
    Activations Density 0.120%

    No Known Activations