© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    pronunciation or saying words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    hest
    -0.22
    WARD
    -0.21
    ä¸Ŀ毫ä¸į
    -0.19
    ward
    -0.19
    Brains
    -0.19
    raquo
    -0.19
    HeaderValue
    -0.18
    ëĭ¨
    -0.18
    eci
    -0.18
    midd
    -0.18
    POSITIVE LOGITS
    itÃł
    0.24
    ity
    0.21
    isse
    0.20
    itemap
    0.20
    pad
    0.19
    imedia
    0.19
    /view
    0.19
    ation
    0.19
    yc
    0.19
    ellido
    0.19
    Activations Density 0.005%

    No Known Activations