© 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. 5436
    Prev
    Next
    INDEX
    Explanations

    to use, copy, modify

    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
    主ä½ĵ责任
    -0.09
    å¶
    -0.08
    inous
    -0.08
    èģĮä¸ļçĶŁæ¶¯
    -0.08
    æĪIJå°±æĦŁ
    -0.08
    ä¸İæŶ
    -0.08
    å¾ħéģĩ
    -0.08
    Boxes
    -0.08
    çģ«çĤ¬
    -0.08
    ç»ı纪人
    -0.08
    POSITIVE LOGITS
    illard
    0.11
    ilate
    0.09
    éĩįä¸Ń
    0.09
    渡
    0.09
    é«ĺå±±
    0.09
    _ASCII
    0.08
    иÑĤелÑĮн
    0.08
     Quincy
    0.08
     ÑģÑĤоÑĢ
    0.08
    _quit
    0.08
    Activations Density 0.002%

    No Known Activations