© 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. 15479
    Prev
    Next
    INDEX
    Explanations

    minutes and seconds formats

    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
    æĻļ
    -0.21
    è¡Įä¸ļåįıä¼ļ
    -0.19
    è¹Ī
    -0.19
    èĪ¶
    -0.18
    è¿ĻæĿ¡
    -0.17
    诱æĥij
    -0.17
    åī¥
    -0.17
    filer
    -0.17
    icies
    -0.17
    /foo
    -0.17
    POSITIVE LOGITS
    AK
    0.20
    lays
    0.19
    aka
    0.18
     Burgess
    0.18
     Termin
    0.18
    以人为
    0.18
    çĨĬ
    0.18
    æī§æĶ¿
    0.17
    çIJĨäºĭéķ¿
    0.17
    ä¹Ĵä¹ĵ
    0.17
    Activations Density 0.020%

    No Known Activations