© 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. 17102
    Prev
    Next
    INDEX
    Explanations

    potato and tomato

    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
    Negative Logits
    ned
    -0.23
    ures
    -0.17
    ness
    -0.17
    urer
    -0.16
    upt
    -0.16
    ë¥ł
    -0.16
    sheets
    -0.16
    no
    -0.16
    nos
    -0.16
    enticated
    -0.15
    POSITIVE LOGITS
    ees
    0.20
    eer
    0.19
    ting
    0.18
    _VIRTUAL
    0.17
    aceous
    0.17
    croft
    0.17
    ÑĤеÑĢ
    0.17
    orus
    0.16
    _SELF
    0.16
    e
    0.16
    Activations Density 0.003%

    No Known Activations