© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59137
    Prev
    Next
    INDEX
    Explanations

    CPU processor names and types

    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
    èıĬèĬ±
    -0.10
     cloned
    -0.09
    esModule
    -0.09
    çģ¶
    -0.09
    mas
    -0.09
    åĴĮåıijå±ķ
    -0.09
    æĿĥçĽĬ
    -0.09
    å¿Ŀ
    -0.09
    UMB
    -0.09
    ä¸ĢæŶ
    -0.09
    POSITIVE LOGITS
     Whit
    0.09
    иÑĢов
    0.09
    æŀĦçŃij
    0.09
    ä½ĨæĪij
    0.09
     whit
    0.09
    PA
    0.08
    éĺ¶
    0.08
     Newport
    0.08
    æŀĭ
    0.08
    .viewport
    0.08
    Activations Density 0.174%

    No Known Activations