© 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. 5332
    Prev
    Next
    INDEX
    Explanations

    fractions with units

    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
     влаÑģÑĤи
    -0.10
    亡
    -0.09
    _CB
    -0.09
    ä¸Ŀä¸Ŀ
    -0.09
    qli
    -0.09
    èĦĸ
    -0.09
    ç°§
    -0.09
    ece
    -0.09
    è£Ĥç¼Ŀ
    -0.09
    chandle
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.10
    ellig
    0.09
    /top
    0.08
    å¼ıçļĦ
    0.08
    ÙĬÙĨØ©
    0.08
    å®Ļ
    0.08
    äºĨä»ĸçļĦ
    0.08
     Curt
    0.07
     Bund
    0.07
    /full
    0.07
    Activations Density 0.057%

    No Known Activations