© 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. 27150
    Prev
    Next
    INDEX
    Explanations

    gillet, vitteta, okket, saket, omet

    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
    itt
    -0.10
     kiá»ĩn
    -0.10
    sat
    -0.10
    sword
    -0.09
    sheet
    -0.09
    sure
    -0.09
    srv
    -0.09
    ç»Ŀ
    -0.09
    è¯ĺ
    -0.09
    res
    -0.09
    POSITIVE LOGITS
    ting
    0.17
    tings
    0.16
    ters
    0.15
    TING
    0.13
    íĮħ
    0.13
    tdown
    0.12
    ted
    0.12
    ech
    0.12
    ius
    0.11
    eker
    0.11
    Activations Density 0.146%

    No Known Activations