© 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. 55690
    Prev
    Next
    INDEX
    Explanations

    clientele, followers, or bases

    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
    most
    -0.09
    outs
    -0.08
    å¤ĸå©Ĩ
    -0.08
    ç£ģåľº
    -0.08
    ly
    -0.08
    ance
    -0.08
    ists
    -0.08
    олоÑģ
    -0.08
    ëĭ¹
    -0.08
    ette
    -0.08
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.09
    åĸĿæ°´
    0.09
    ç¾İèªī
    0.09
    erved
    0.09
    åIJĦå¼ıåIJĦæł·
    0.09
    geb
    0.09
    rome
    0.09
     olacaģı
    0.09
    ä»İ容
    0.08
    å¿ĥ缮ä¸Ń
    0.08
    Activations Density 0.021%

    No Known Activations