© 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. 27166
    Prev
    Next
    INDEX
    Explanations

    consulting

    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
    -0.14
    lish
    -0.09
    quis
    -0.09
    .locale
    -0.09
    iac
    -0.09
    ansas
    -0.09
    ör
    -0.08
    常å§Ķä¼ļ
    -0.08
    clud
    -0.08
    åĴĮå®ĮåĸĦ
    -0.08
    POSITIVE LOGITS
    หาร
    0.11
    ÑĤин
    0.11
    ego
    0.10
    пан
    0.10
    agr
    0.10
     Ùħصدر
    0.09
    ainter
    0.09
    ibration
    0.09
    езн
    0.09
    羯
    0.09
    Activations Density 0.018%

    No Known Activations