© 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. 6008
    Prev
    Next
    INDEX
    Explanations

    extr with an, ous, or ing

    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
    ings
    -0.10
    ãģ£ãģ±
    -0.10
    peed
    -0.09
    uration
    -0.09
    rade
    -0.09
    æĺĶ
    -0.09
    ätze
    -0.08
    olina
    -0.08
    old
    -0.08
    ço
    -0.08
    POSITIVE LOGITS
    ized
    0.11
    ities
    0.10
    éģij
    0.10
    áln
    0.09
    髹
    0.09
    FileSync
    0.09
    å®īçĦ¶
    0.09
    ındaki
    0.09
     ReSharper
    0.09
    åIJĦæł·
    0.09
    Activations Density 0.007%

    No Known Activations