© 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. 15445
    Prev
    Next
    INDEX
    Explanations

    Rockefeller, Lockheed, Pixar, Oil

    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
    ware
    -0.19
    iful
    -0.18
    ing
    -0.17
    esz
    -0.17
    fully
    -0.17
    match
    -0.17
    wear
    -0.17
    OfWeek
    -0.17
    finding
    -0.16
    /false
    -0.16
    POSITIVE LOGITS
    angelo
    0.18
    berman
    0.17
    inox
    0.17
    ibern
    0.17
    mpr
    0.16
    изаÑĨиÑı
    0.16
    å¤ĸ交éĥ¨
    0.16
    æ³·
    0.16
     brushes
    0.16
    legt
    0.16
    Activations Density 0.006%

    No Known Activations