© 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. 16290
    Prev
    Next
    INDEX
    Explanations

    NCAA Division I, II, III

    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
    åIJı
    -0.23
     enumerator
    -0.21
    Ãłng
    -0.20
    cheon
    -0.19
    åľ¨æ¸¸æĪıä¸Ń
    -0.19
    ildo
    -0.18
    anter
    -0.17
    _DISP
    -0.17
    .dump
    -0.17
    æijĬ
    -0.17
    POSITIVE LOGITS
    èIJ¥åĪ©
    0.23
    èģĶèµĽ
    0.22
     League
    0.22
    çŃī级
    0.21
    æłĩåĩĨ
    0.21
    éĻ¢æł¡
    0.20
    è¡Ķ
    0.20
     league
    0.20
    èģĭ
    0.20
    -level
    0.19
    Activations Density 0.004%

    No Known Activations