© 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. 12935
    Prev
    Next
    INDEX
    Explanations

    range of motion, physical actions

    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
    å¸ĥå±Ģ
    -0.21
    Keyword
    -0.20
    yme
    -0.20
    elles
    -0.19
    é£İ鼨
    -0.19
    APER
    -0.18
    éĢīåĿĢ
    -0.18
    æĪĺçķ¥å¸ĥå±Ģ
    -0.18
    .avg
    -0.18
    oy
    -0.18
    POSITIVE LOGITS
    åıĹéĻIJ
    0.27
    acin
    0.24
    诱åıij
    0.21
     state
    0.20
    _builtin
    0.19
    è¿IJåĬ¨ä¼ļ
    0.19
    æĬļæij¸
    0.19
    çĪIJ
    0.19
    åıĹå½±åĵį
    0.19
    åĽ¹
    0.19
    Activations Density 0.048%

    No Known Activations