© 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. 18577
    Prev
    Next
    INDEX
    Explanations

    classified and secret information

    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
    èIJ½
    -0.09
    _counters
    -0.09
    dale
    -0.09
    ì¦Ī
    -0.09
    .sav
    -0.09
    доÑĢ
    -0.09
    åij¨æľŁ
    -0.08
    æŁ¥çľĭåħ¨æĸĩ
    -0.08
    åįĥä¸ĩ
    -0.08
    ibbon
    -0.08
    POSITIVE LOGITS
    讳
    0.10
    ä¸ĢåĪĻ
    0.09
    /private
    0.09
    å®ľ
    0.09
    crow
    0.09
    ä¸Ńå°ıåŀĭ
    0.09
     Onion
    0.08
    稽
    0.08
    esc
    0.08
     stuff
    0.08
    Activations Density 0.012%

    No Known Activations