© 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. 53571
    Prev
    Next
    INDEX
    Explanations

    in detail

    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
    羣åĪĩ
    -0.11
    ÑģÑĤо
    -0.09
    иÑĩеÑģки
    -0.08
    .writer
    -0.08
    çķĭ
    -0.08
    amd
    -0.08
    gba
    -0.08
    BeginInit
    -0.08
     pog
    -0.08
    åĤ¬
    -0.08
    POSITIVE LOGITS
    bach
    0.10
    äºĨä»ĸçļĦ
    0.09
    åĩĨå¤ĩ好
    0.08
    æ¼ķ
    0.08
    åĽ½æ°ijç»ıæµİ
    0.08
    äºĨåIJĹ
    0.08
    ville
    0.08
    滿足
    0.08
    åħ«ä¸ª
    0.08
    mates
    0.08
    Activations Density 0.019%

    No Known Activations