© 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. 13958
    Prev
    Next
    INDEX
    Explanations

    events and distances

    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
    ORMAL
    -0.21
    ç»ħ
    -0.19
    kim
    -0.19
    åĩºåĵģ
    -0.18
     ting
    -0.18
     certain
    -0.18
    æĢ»ä½ĵ
    -0.18
     prior
    -0.18
    ZE
    -0.17
    _-_
    -0.17
    POSITIVE LOGITS
    ä¸ī项
    0.25
    æľ¬æĬ¥
    0.22
    æľĢéķ¿
    0.21
    è¯ķçĤ¹å·¥ä½ľ
    0.20
    éļľç¢į
    0.20
    åIJ¬åIJ¬
    0.20
    åıĮèĦļ
    0.20
    çĭ¬è§Ĵåħ½
    0.20
    éĩįåŀĭ
    0.20
    两项
    0.19
    Activations Density 0.033%

    No Known Activations