© 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. 10949
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    amon
    -0.21
    æ¶ħ
    -0.21
    Facade
    -0.21
    çļĦ羣å®ŀ
    -0.20
    åĽ¢ä½ĵ
    -0.20
    ç·
    -0.19
    fortunately
    -0.19
    é¼İ
    -0.19
    èĵī
    -0.18
     exhaust
    -0.18
    POSITIVE LOGITS
    åŃĹ第
    0.20
    èĻı
    0.20
    车å±ķ
    0.19
    ynam
    0.19
    éĺĤ
    0.19
    é¢Ĩåıĸ
    0.18
    ãģļ
    0.18
    ftype
    0.18
     lem
    0.18
    åĪĨãģij
    0.18
    Activations Density 0.001%

    No Known Activations