© 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. 6405
    Prev
    Next
    INDEX
    Explanations

    programming and game companies

    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
    èĢĮåİ»
    -0.08
    注éĩį
    -0.08
    æĪijåıĪ
    -0.08
    éĩįè§Ĩ
    -0.08
    èĮij
    -0.08
    çĪ¬ä¸Ĭ
    -0.08
    æĹĮ
    -0.08
    inqu
    -0.08
     POP
    -0.08
    çļĦæķ´ä½ĵ
    -0.08
    POSITIVE LOGITS
    èį¯æĿIJ
    0.10
    å·¡åĽŀ
    0.09
    æŶå°ļ
    0.09
    å½ĵä¸ĭ
    0.09
    ç¢İçīĩ
    0.09
    oyal
    0.09
    .backward
    0.08
    lsi
    0.08
    YTE
    0.08
    çĮľæĥ³
    0.08
    Activations Density 0.001%

    No Known Activations