© 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. 27889
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    ç½Ĥ
    -0.10
    velt
    -0.10
    åĵī
    -0.10
    zion
    -0.09
    .hasClass
    -0.09
    оÑĦ
    -0.09
    vore
    -0.09
    ManagerInterface
    -0.09
    اخبار
    -0.09
    ))->
    -0.09
    POSITIVE LOGITS
    æŃ£åĢ¼
    0.09
    å¥ijæľº
    0.08
    ä¸ĭ鼨
    0.08
    éļ°
    0.08
    è°Īè¯Ŀ
    0.08
    éĹ²
    0.08
    ä¸įæĿ¥
    0.08
    äºijéĽĨ
    0.08
    åĪĥ
    0.08
    ä¸įèµ·
    0.08
    Activations Density 0.088%

    No Known Activations