© 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. 48563
    Prev
    Next
    INDEX
    Explanations

    were followed by questions or descriptions of states

    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
    s
    -0.18
    ly
    -0.15
    nya
    -0.13
    ned
    -0.12
    es
    -0.11
    sWith
    -0.11
    ses
    -0.11
    é
    -0.11
    ments
    -0.10
    né
    -0.10
    POSITIVE LOGITS
    ÑģÑĤÑĮ
    0.14
    обÑĢаз
    0.12
    geist
    0.12
    ester
    0.11
    isque
    0.11
    affle
    0.11
    ofday
    0.10
    оÑĢ
    0.10
    ght
    0.10
    hip
    0.10
    Activations Density 0.137%

    No Known Activations