© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    leave to file

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ships
    -0.24
    ually
    -0.23
    ific
    -0.22
    smith
    -0.21
    series
    -0.21
    set
    -0.20
    lov
    -0.19
    lover
    -0.19
    ians
    -0.19
    ãģªãĤĬ
    -0.18
    POSITIVE LOGITS
    abouts
    0.27
    hin
    0.20
    overs
    0.20
    /right
    0.19
    hard
    0.18
    åİ¢
    0.18
    aug
    0.18
    nard
    0.18
    -taking
    0.18
    e
    0.18
    Activations Density 0.036%

    No Known Activations