© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    bun or hun

    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
    人士
    -0.20
    ystone
    -0.19
    ever
    -0.19
    çĴł
    -0.19
    æѤå¤Ħ
    -0.18
    een
    -0.18
    éķ§
    -0.17
    ein
    -0.17
    CHIP
    -0.17
    äm
    -0.17
    POSITIVE LOGITS
    yard
    0.24
    ย
    0.23
    ners
    0.23
    ions
    0.22
    iversal
    0.21
    lard
    0.21
    idades
    0.21
    robots
    0.20
    sville
    0.20
    aries
    0.20
    Activations Density 0.013%

    No Known Activations