© 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. 13312
    Prev
    Next
    INDEX
    Explanations

    substances

    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
    ðŁı»
    -0.18
    æ¼ĵ
    -0.17
    creen
    -0.17
    side
    -0.17
    wards
    -0.17
    coming
    -0.17
    ç¿İ
    -0.17
    å¾Ĺ太
    -0.17
    è¿ĩçļĦ
    -0.17
    ä½Ĩä¸įéĻIJ
    -0.17
    POSITIVE LOGITS
    UnderTest
    0.26
    hood
    0.23
    çļ¿
    0.20
    hip
    0.20
    åIJį称
    0.19
    (s
    0.19
    als
    0.19
    orem
    0.19
    /method
    0.19
    ives
    0.18
    Activations Density 0.426%

    No Known Activations