© 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. 16439
    Prev
    Next
    INDEX
    Explanations

    role of

    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
    ÑĮÑİ
    -0.17
    æ²¥
    -0.16
    iator
    -0.16
    æĪ·åı£
    -0.16
    ħ
    -0.16
    lâ
    -0.16
     Airways
    -0.16
    dem
    -0.16
    /mit
    -0.15
    ãģĹãģ¾ãģĨ
    -0.15
    POSITIVE LOGITS
    fully
    0.24
    less
    0.21
    lessness
    0.21
    æī®æ¼Ķ游æĪı
    0.20
    istic
    0.19
    idon
    0.17
    swith
    0.17
    letes
    0.17
    pen
    0.17
    é¬ĵ
    0.17
    Activations Density 0.045%

    No Known Activations