© 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. 10588
    Prev
    Next
    INDEX
    Explanations

    McMahon, Anni, Huxley

    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
    ä¸Ģ侧
    -0.09
    åıªè¦ģæľī
    -0.08
    Exporter
    -0.08
    åĪĨè£Ĥ
    -0.08
     Souls
    -0.08
    åĬ«
    -0.08
    dde
    -0.08
    èĸĦ
    -0.08
    被èªī
    -0.08
     Len
    -0.08
    POSITIVE LOGITS
    ä¸įåĪĨ
    0.10
    æŁ¥çľĭåħ¨æĸĩ
    0.08
    æĹĥ
    0.08
    夫人
    0.08
    亥
    0.08
    æĸ°ä¸ī
    0.08
    ä¾¿å®ľ
    0.08
    mobile
    0.08
    æ¸Į
    0.08
     pound
    0.08
    Activations Density 0.073%

    No Known Activations