© 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. 57615
    Prev
    Next
    INDEX
    Explanations

    particularly sensitive or functional

    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
    ç®Ģ缴æĺ¯
    -0.11
     Wat
    -0.09
    илÑĮ
    -0.09
    ally
    -0.09
    åĨ³ä¸į
    -0.09
    ç®Ģ缴
    -0.08
    ä¸ĩ象
    -0.08
    rot
    -0.08
    äºĭä¸ļåįķä½į
    -0.08
    éĩįéĩį
    -0.08
    POSITIVE LOGITS
    åī©
    0.10
    æĽĻ
    0.10
    åī©ä¸ĭ
    0.09
    thic
    0.09
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.09
    éŨåīį
    0.08
    رÙĤ
    0.08
    -grand
    0.08
    Vi
    0.08
    ordin
    0.08
    Activations Density 0.002%

    No Known Activations