© 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. 11462
    Prev
    Next
    INDEX
    Explanations

    physical locations and requirements

    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
    åĢĴåľ¨
    -0.21
    èº²åľ¨
    -0.20
    éļ¶
    -0.20
     borderline
    -0.20
     Basket
    -0.19
    æ®ī
    -0.19
    èººåľ¨åºĬä¸Ĭ
    -0.19
    çļĦ人çī©
    -0.19
    åij±
    -0.19
    马æĭī
    -0.19
    POSITIVE LOGITS
    iami
    0.21
    ä¸įä¼ļæľī
    0.19
    veis
    0.19
    aker
    0.19
    xBB
    0.19
    å¾Ħ
    0.19
    å±ĭåŃIJ
    0.19
    ç¶ļ
    0.19
    endon
    0.19
    (QStringLiteral
    0.19
    Activations Density 0.017%

    No Known Activations