© 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. 62878
    Prev
    Next
    INDEX
    Explanations

    festival and event lineup

    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
    éĺ³åı°
    -0.09
     studio
    -0.09
    abinet
    -0.09
    æľĪä¸ĭ
    -0.09
     зай
    -0.09
    å¤ĸæĿ¥
    -0.09
    èħĬ
    -0.08
    æĪ·åŀĭ
    -0.08
    hone
    -0.08
    èĥĮ
    -0.08
    POSITIVE LOGITS
    大ä¼ļ
    0.10
    session
    0.10
     sessions
    0.10
    第ä¸Ģ天
    0.10
     session
    0.10
    _sessions
    0.09
     Sessions
    0.09
    第äºĶå±Ĭ
    0.09
     Organizer
    0.09
    æ¯Ķä¸Ĭå¹´
    0.09
    Activations Density 0.204%

    No Known Activations