© 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. 4656
    Prev
    Next
    INDEX
    Explanations

    provider who

    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
    пÑĢом
    -0.10
    abinet
    -0.09
    ä½į
    -0.09
    earing
    -0.08
    _VALUES
    -0.08
     convent
    -0.08
    æīĢåľ¨çļĦ
    -0.08
    ear
    -0.08
    uated
    -0.08
    ãĥ³ãĥī
    -0.08
    POSITIVE LOGITS
    wis
    0.10
    rsa
    0.09
    datum
    0.09
    esso
    0.09
    æľ
    0.08
    ложен
    0.08
    ëĭĺ
    0.08
    utors
    0.08
    åĨµä¸Ķ
    0.08
    apis
    0.08
    Activations Density 0.024%

    No Known Activations