© 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. 48101
    Prev
    Next
    INDEX
    Explanations

    Depot and application

    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
    -0.11
    sam
    -0.10
    æĬ¥éħ¬
    -0.10
    enal
    -0.09
    pool
    -0.09
    REA
    -0.09
    é¦Ĩ
    -0.09
    berger
    -0.08
    ãģĦãģĨ
    -0.08
    ãģıãĤĭ
    -0.08
    POSITIVE LOGITS
    geist
    0.10
    theon
    0.10
    olv
    0.09
    ÑĤоÑĢ
    0.09
    mental
    0.09
    æ¶ķ
    0.09
    olis
    0.09
    wards
    0.09
    antar
    0.09
    巴士
    0.09
    Activations Density 0.002%

    No Known Activations