© 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. 31401
    Prev
    Next
    INDEX
    Explanations

    Technical Field

    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
    æķ´æ´ģ
    -0.09
    aire
    -0.09
    次æķ°
    -0.09
    DEM
    -0.09
    ichael
    -0.08
    èĺĸ
    -0.08
    å±Ĩ
    -0.08
     Ney
    -0.08
     phenomen
    -0.08
    croll
    -0.08
    POSITIVE LOGITS
    åIJ«éĩı
    0.13
    å¯ĨéĽĨ
    0.10
    åĴĮæĬĢæľ¯
    0.09
    å´ĩæĭľ
    0.09
    alley
    0.09
    ä¸įçŁ¥ä¸įè§ī
    0.09
    åĴĮæľįåĬ¡
    0.09
     technical
    0.08
    åĴĮ社ä¼ļ
    0.08
    们éĥ½
    0.08
    Activations Density 0.078%

    No Known Activations