© 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. 11515
    Prev
    Next
    INDEX
    Explanations

    although it

    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
    edly
    -0.22
    æīĢ以æĪij
    -0.20
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.20
    å¦Ĥä½ķ
    -0.18
    jal
    -0.17
    esh
    -0.17
    ç»Īäºİ
    -0.16
    ãģ»ãģ©
    -0.16
    æīĢä»¥åľ¨
    -0.16
    olid
    -0.15
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.18
    /out
    0.18
    æĻ°
    0.18
    å¾Īæĥ³
    0.17
    eus
    0.17
    大家éĥ½åľ¨
    0.17
    soever
    0.17
    onso
    0.16
    ä¸Ģå®ļçļĦ
    0.16
     ë¶Ī구íķĺê³ł
    0.16
    Activations Density 0.020%

    No Known Activations