© 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. 15789
    Prev
    Next
    INDEX
    Explanations

    down payment or Anthony Bledsoe or <?xml

    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
     kin
    -0.20
    éĭĨ
    -0.19
    inker
    -0.19
    UnderTest
    -0.19
    _CLOSED
    -0.19
     Ink
    -0.18
    ç²Ĺ
    -0.18
    èº²åľ¨
    -0.18
    å¼Ī
    -0.18
    pret
    -0.18
    POSITIVE LOGITS
    compress
    0.19
     swe
    0.19
    带ä¸Ĭ
    0.19
    ecurity
    0.19
    è´Ń车
    0.18
    买车
    0.18
    çļİ
    0.18
    éĺģ
    0.18
    è´ŀ
    0.18
    èĵ¼
    0.18
    Activations Density 0.006%

    No Known Activations