© 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. 54483
    Prev
    Next
    INDEX
    Explanations

    medical and scientific journals

    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
    åĬª
    -0.09
    LETE
    -0.08
    RITE
    -0.08
    pite
    -0.08
    ä¸Ģç¬Ķ
    -0.08
    ä¸Ģè¶Ł
    -0.08
    é¤IJé¦Ĩ
    -0.08
    éħį
    -0.08
    ä»Ģä¹ĪåİŁåĽł
    -0.07
    moz
    -0.07
    POSITIVE LOGITS
     namedtuple
    0.10
    IOS
    0.09
    樽
    0.09
    æĿĤå¿Ĺ
    0.09
    à¤Ŀ
    0.09
    ssi
    0.09
    csr
    0.09
    奸
    0.09
    _charset
    0.09
    åIJĮæĦı
    0.09
    Activations Density 0.156%

    No Known Activations