© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22239
    Prev
    Next
    INDEX
    Explanations

    cattle

    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
    ingly
    -0.11
    åĦ¿
    -0.11
    åįģ足
    -0.10
    nes
    -0.10
    enstein
    -0.09
    ners
    -0.09
    nen
    -0.09
    ../../../
    -0.09
    å¥Ń
    -0.09
    edi
    -0.09
    POSITIVE LOGITS
    /or
    0.14
    levision
    0.10
    /she
    0.09
    ENE
    0.09
    pole
    0.09
    é»į
    0.09
    itta
    0.08
    alker
    0.08
    æĥĬ人
    0.08
    ä¸Ģçľĭ
    0.08
    Activations Density 0.007%

    No Known Activations