© 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. 6209
    Prev
    Next
    INDEX
    Explanations

    comic book

    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
    Negative Logits
    ted
    -0.09
    abouts
    -0.09
    ate
    -0.09
    ning
    -0.09
    imer
    -0.09
    immer
    -0.09
    KA
    -0.09
    年轻人
    -0.08
    ume
    -0.08
    ATE
    -0.08
    POSITIVE LOGITS
    plx
    0.11
    urve
    0.10
    ../
    0.09
    oola
    0.09
     minded
    0.09
    ophone
    0.09
    sterol
    0.09
    idis
    0.09
    rete
    0.09
    »
    0.09
    Activations Density 0.008%

    No Known Activations