© 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. 1837
    Prev
    Next
    INDEX
    Explanations

    Minnesota and its associated entities

    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
    ../../../
    -0.10
    æľ¬ç«Ļ
    -0.10
    çĦ¶æĺ¯
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
     gắng
    -0.09
    culate
    -0.09
    aceous
    -0.09
    ier
    -0.09
    teen
    -0.08
    å®ģ
    -0.08
    POSITIVE LOGITS
    chia
    0.11
    eton
    0.10
    IMUM
    0.10
    zer
    0.09
     Mesa
    0.09
    erner
    0.09
    iesen
    0.09
    моÑĢ
    0.09
    ĭ
    0.09
    enance
    0.09
    Activations Density 0.022%

    No Known Activations