© 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. 30213
    Prev
    Next
    INDEX
    Explanations

    flex-layout/flexbox/flexure

    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
     Burb
    -0.08
     Fake
    -0.08
    noon
    -0.08
    venir
    -0.08
    'S
    -0.08
    èĬĤ
    -0.08
    bling
    -0.08
    omi
    -0.08
    acks
    -0.08
    .GetService
    -0.07
    POSITIVE LOGITS
    ibly
    0.12
    iras
    0.11
    ural
    0.11
    ibility
    0.10
    ently
    0.10
    IRON
    0.10
    á»Ń
    0.10
    pected
    0.09
    ìĤ¬íķŃ
    0.09
    umbo
    0.09
    Activations Density 0.053%

    No Known Activations