© 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. 15054
    Prev
    Next
    INDEX
    Explanations

    less

    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
    _fence
    -0.20
    å¤Ł
    -0.20
    éĺ¡
    -0.19
     wÅĤaÅĽnie
    -0.19
    å¤ł
    -0.18
    emes
    -0.18
    æ¼ıæ°´
    -0.17
    éĵµ
    -0.17
    车主
    -0.17
     Hutch
    -0.17
    POSITIVE LOGITS
    less
    0.29
    ä¸İåIJ¦
    0.26
    -less
    0.25
    lessness
    0.24
    çļĦæĥħåĨµä¸ĭ
    0.22
    LESS
    0.20
    lessly
    0.19
    ä¸Ĭä¸ĭ
    0.19
    ä½Ĩ对äºİ
    0.19
    Enabled
    0.19
    Activations Density 0.274%

    No Known Activations