© 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. 56964
    Prev
    Next
    INDEX
    Explanations

    life with

    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
    è¸Ł
    -0.09
    笼
    -0.09
    åĵij
    -0.09
    æ¸İ
    -0.09
    é¢ĺ主
    -0.09
    edia
    -0.09
    åİĨåı²ä¸Ĭ
    -0.09
    æ£į
    -0.08
    æ»ļ
    -0.08
    -pad
    -0.08
    POSITIVE LOGITS
    å±ĭ
    0.09
    PTY
    0.08
    æ¯ķä¸ļåIJİ
    0.08
    ä¸ĢåIJ¬
    0.08
    å®ł
    0.08
     tats
    0.08
    gra
    0.08
    деÑĤ
    0.07
    å®Ĺ
    0.07
    饴
    0.07
    Activations Density 0.035%

    No Known Activations