© 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. 11758
    Prev
    Next
    INDEX
    Explanations

    official notices and opinions

    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
    imately
    -0.21
     literal
    -0.20
    ä¸ĢæĹ¥
    -0.19
     pl
    -0.19
    举
    -0.19
    æ§ĺ
    -0.19
    !?
    -0.18
     transformed
    -0.18
    为人
    -0.18
    âĺŀ
    -0.18
    POSITIVE LOGITS
    æŃ£æĸĩ
    0.21
    HOOK
    0.21
    ê·Ģ
    0.20
    _minute
    0.20
    èĪIJ
    0.19
    æµ£
    0.19
    ="__
    0.19
    .Escape
    0.19
    èĩĨ
    0.18
    esture
    0.18
    Activations Density 0.006%

    No Known Activations