© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15168
    Prev
    Next
    INDEX
    Explanations

    ever, yet, history, record

    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
    _PROVID
    -0.21
    个æĢ§
    -0.20
    ä¼ĺç§Ģ
    -0.20
    æĩ¿
    -0.20
    å¤Ħå¤Ħ
    -0.20
    å¾Ĺ天çĭ¬åİļ
    -0.19
    åİŁåĪĽ
    -0.19
     flesh
    -0.19
    _optional
    -0.18
    _byte
    -0.18
    POSITIVE LOGITS
    æŃ¤æ¬¡
    0.21
    ä¸ļåĬ¡
    0.20
    /tiny
    0.20
     Fond
    0.19
    åľºéĿ¢
    0.19
    AAAAAAAA
    0.19
    è§Ħ模
    0.19
    æ¥ŃåĭĻ
    0.19
    business
    0.18
    بش
    0.18
    Activations Density 0.020%

    No Known Activations