© 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. 31858
    Prev
    Next
    INDEX
    Explanations

    brand or generic labels

    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
    endet
    -0.09
    æıIJåīį
    -0.09
    éļĶ
    -0.09
    é½IJ
    -0.08
    æıIJæĹ©
    -0.08
    punk
    -0.08
    alem
    -0.08
    enden
    -0.08
    åIJĮæľŁ
    -0.08
    åħ¥æīĭ
    -0.08
    POSITIVE LOGITS
    åĵģçīĮçļĦ
    0.13
    åĵģçīĮ
    0.13
     branding
    0.13
    -brand
    0.13
     brands
    0.13
    brand
    0.12
     brand
    0.11
    ãĥĸãĥ©ãĥ³ãĥī
    0.11
     branded
    0.11
    èĩªä¸»åĵģçīĮ
    0.11
    Activations Density 0.105%

    No Known Activations