© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53374
    Prev
    Next
    INDEX
    Explanations

    val followed by di, in, or leys

    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
    edes
    -0.12
    ä¹į
    -0.10
    ../../../
    -0.10
    weis
    -0.09
    ening
    -0.09
    åĺı
    -0.09
    ester
    -0.09
    ivity
    -0.09
    esters
    -0.09
    ationToken
    -0.09
    POSITIVE LOGITS
    uetype
    0.12
    uess
    0.12
    Ŀ
    0.10
    leys
    0.10
    еж
    0.10
    æ¯Ķäºļ
    0.10
    entina
    0.09
    entin
    0.09
     Crimson
    0.09
    ä½ĵç³»
    0.09
    Activations Density 0.047%

    No Known Activations