© 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. 21474
    Prev
    Next
    INDEX
    Explanations

    any other

    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
    fter
    -0.10
    ä¹ĭæĹħ
    -0.09
    ç»ıçIJĨ
    -0.09
    æĺ¯å¦Ĥä½ķ
    -0.09
    nes
    -0.08
    æĺ¯å¤ļä¹Ī
    -0.08
    athe
    -0.08
    ble
    -0.08
     Hub
    -0.08
    缴æݥ影åĵį
    -0.08
    POSITIVE LOGITS
    çijķ
    0.11
    åĵ¨
    0.09
    ä¸Ģç§į
    0.09
    uggy
    0.09
    THING
    0.09
    ä¸Ģ種
    0.08
    ÙħÙĪÙĨ
    0.08
    ÑĪÑĥ
    0.08
    饴
    0.08
    bish
    0.08
    Activations Density 0.038%

    No Known Activations