© 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. 39702
    Prev
    Next
    INDEX
    Explanations

    internet and digital services

    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
    atorio
    -0.09
    æ¢Ń
    -0.09
    ç§ĭåŃ£
    -0.09
    èIJ½åı¶
    -0.08
    èµ°åİ»
    -0.08
     Fall
    -0.08
    å²IJ
    -0.08
    OTE
    -0.08
    illis
    -0.08
    æĭį
    -0.08
    POSITIVE LOGITS
    ä¸į失
    0.09
     interactive
    0.09
    èİ«æĸ¯
    0.09
    interactive
    0.09
    å²ļ
    0.09
    éļĶ
    0.08
    åĢį
    0.08
     <![
    0.08
    IFEST
    0.08
    ipur
    0.08
    Activations Density 0.159%

    No Known Activations