© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19920
    Prev
    Next
    INDEX
    Explanations

    link="#

    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
    cho
    -0.09
    rim
    -0.08
     reap
    -0.08
    éĢļé£İ
    -0.08
    wie
    -0.08
    pipes
    -0.08
    CHO
    -0.08
    ypsy
    -0.08
    viz
    -0.08
    æѦè£ħ
    -0.08
    POSITIVE LOGITS
    èĿĩ
    0.12
    yard
    0.11
    quez
    0.10
    atile
    0.10
    ç»ıåİĨ
    0.09
     commod
    0.09
    yards
    0.09
    olumn
    0.09
    0.09
    åĬ²
    0.08
    Activations Density 0.579%

    No Known Activations