© 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. 17650
    Prev
    Next
    INDEX
    Explanations

    adhere to

    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
    ted
    -0.12
    ting
    -0.10
    tle
    -0.10
    ton
    -0.09
    ï¸ı
    -0.09
    fic
    -0.09
    iling
    -0.09
    loi
    -0.09
    naire
    -0.08
    wel
    -0.08
    POSITIVE LOGITS
    ance
    0.12
    roit
    0.11
    icit
    0.11
    ìĤ¬íķŃ
    0.11
    quate
    0.11
    ents
    0.10
    vertise
    0.10
    hé
    0.09
    itung
    0.09
    elian
    0.09
    Activations Density 0.018%

    No Known Activations