© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11342
    Prev
    Next
    INDEX
    Explanations

    copyright ownership

    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
    lets
    -0.21
    åŃIJéĩĮ
    -0.20
    ÑĩаÑĤ
    -0.20
    VML
    -0.19
    uated
    -0.19
    uation
    -0.19
    sWith
    -0.18
    =-=-=-=-=-=-=-=-
    -0.18
    odem
    -0.18
    çħ³
    -0.17
    POSITIVE LOGITS
    hip
    0.25
    éĩı
    0.19
    hin
    0.19
    htdocs
    0.18
    hid
    0.17
    ep
    0.17
    hy
    0.17
    hare
    0.16
     Tanz
    0.16
    ize
    0.16
    Activations Density 0.006%

    No Known Activations