© 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. 48667
    Prev
    Next
    INDEX
    Explanations

    Buffy, Django, andy, indy, jango names

    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
    æĺ¯ä»ĸ
    -0.09
    庶
    -0.09
    -www
    -0.09
     dolayı
    -0.08
    aries
    -0.08
    âĨĻ
    -0.08
     overs
    -0.08
    dden
    -0.08
    size
    -0.08
    ned
    -0.08
    POSITIVE LOGITS
    оÑģÑĮ
    0.11
    åıªè¦ģæĺ¯
    0.10
    ulares
    0.10
    ä¸įå°ıçļĦ
    0.09
    ä¸įå¼Ģ
    0.09
    ï¸ı
    0.09
    atics
    0.09
    强çĥĪçļĦ
    0.09
    åIJįå½ķ
    0.09
    ectomy
    0.09
    Activations Density 0.006%

    No Known Activations