© 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. 49806
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
     conf
    -0.09
    ä¸įæŃ»
    -0.09
    æľīæīĢ
    -0.09
    åĮ£
    -0.09
    _latency
    -0.09
    âı³
    -0.09
    æĶ¾æīĭ
    -0.09
    éħĮ
    -0.09
    åijĨ
    -0.09
    漫
    -0.08
    POSITIVE LOGITS
    çĮĹ
    0.09
    å½ķçĶ¨
    0.09
    èĵĦ
    0.08
     Interior
    0.08
    éĹ®é¢ĺæĺ¯
    0.08
    well
    0.08
    nde
    0.08
    ams
    0.08
    pton
    0.08
    ä½ľå¼Ĭ
    0.08
    Activations Density 0.179%

    No Known Activations