© 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. 3206
    Prev
    Next
    INDEX
    Explanations

    trailer

    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
    ERIC
    -0.28
    ters
    -0.24
    书记
    -0.23
    nings
    -0.22
    fully
    -0.21
     volont
    -0.20
    istry
    -0.20
    ertype
    -0.20
    ert
    -0.19
    son
    -0.19
    POSITIVE LOGITS
    hip
    0.26
    -mounted
    0.24
    /mat
    0.23
     cabo
    0.21
    /cpp
    0.20
    å¼ıçļĦ
    0.19
    -fast
    0.19
    åŃIJéĩĮ
    0.19
     apr
    0.19
    -most
    0.19
    Activations Density 0.004%

    No Known Activations