© 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. 32461
    Prev
    Next
    INDEX
    Explanations

    storage devices and media

    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
    ä¸įé«ĺ
    -0.09
    åŃĹæł·
    -0.08
    æ£į
    -0.08
     Bos
    -0.08
    大éħĴåºĹ
    -0.08
     fro
    -0.08
    çIJIJ
    -0.08
     Bush
    -0.08
    Fans
    -0.08
    个å¤ļ
    -0.08
    POSITIVE LOGITS
    literal
    0.10
    entes
    0.10
    ente
    0.09
    OfSize
    0.09
    _FMT
    0.09
    une
    0.09
    ople
    0.09
    æŀĭ
    0.08
    elsen
    0.08
    ATAB
    0.08
    Activations Density 0.037%

    No Known Activations