© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10608
    Prev
    Next
    INDEX
    Explanations

    abbreviations like CI, FI, VI, SI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ski
    -0.22
    ness
    -0.19
    ship
    -0.18
    nya
    -0.17
    oon
    -0.17
    lore
    -0.17
    lying
    -0.17
    ر
    -0.16
    ni
    -0.16
    анд
    -0.16
    POSITIVE LOGITS
    egl
    0.18
    ames
    0.17
    èĩ¾
    0.17
    _processors
    0.16
    -même
    0.16
    udad
    0.15
    cone
    0.15
    iful
    0.15
    -dess
    0.15
    iming
    0.15
    Activations Density 0.075%

    No Known Activations