© 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. 2551
    Prev
    Next
    INDEX
    Explanations

    from the

    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
    æѤ
    -0.13
    æѤå¤Ħ
    -0.12
    æĿ¥èĩª
    -0.12
    ä»İäºĭ
    -0.11
    åīį
    -0.10
    ä¸Ńåħ³æĿij
    -0.10
    æŃ¤äºº
    -0.10
    ä»İ严
    -0.09
    romo
    -0.09
    å°ıåŀĭ
    -0.09
    POSITIVE LOGITS
    /to
    0.22
     afar
    0.17
    /about
    0.15
    ä¸Ģå¼Ģå§ĭå°±
    0.15
    /by
    0.14
    /of
    0.14
    atted
    0.14
     dolayı
    0.13
    ä¸ī个æĸ¹éĿ¢
    0.13
     него
    0.13
    Activations Density 0.359%

    No Known Activations