© 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. 36571
    Prev
    Next
    INDEX
    Explanations

    Bh names

    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
    é«ĺé¢ij
    -0.09
     foil
    -0.09
    hed
    -0.08
    eenth
    -0.08
    DER
    -0.08
    eree
    -0.08
    å¼Ľ
    -0.08
    åħ¼èģĮ
    -0.08
    iol
    -0.07
    unes
    -0.07
    POSITIVE LOGITS
    olum
    0.10
    ably
    0.10
    acter
    0.10
    äºĮåŃĹ
    0.09
    ypad
    0.09
     Affero
    0.09
    份
    0.09
    landır
    0.09
    ä¼Łå¤§å¤įåħ´
    0.09
    rouch
    0.09
    Activations Density 0.019%

    No Known Activations