© 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. 62396
    Prev
    Next
    INDEX
    Explanations

    statement

    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
    ä¸Ģè¶Ł
    -0.10
    åłĩ
    -0.10
    è¿ĺæĮº
    -0.09
    ä»Ģä¹Īéĥ½ä¸į
    -0.09
    heid
    -0.09
    ording
    -0.09
    ä»Ģä¹Īéĥ½
    -0.09
    åľ¨å¹¿å·ŀ
    -0.09
    itized
    -0.09
    uate
    -0.08
    POSITIVE LOGITS
    åĮħåIJ«äºĨ
    0.09
    aries
    0.09
    вели
    0.09
    天ä¸ĭ
    0.09
    é£İåIJ¹
    0.08
    æ¢ħ
    0.08
    Containing
    0.08
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.08
    |array
    0.08
    çijķ
    0.08
    Activations Density 0.007%

    No Known Activations