© 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. 12787
    Prev
    Next
    INDEX
    Explanations

    comment markers

    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
    -0.25
    èĻ½çĦ¶æĺ¯
    -0.21
    ä¹Łå°±æĺ¯è¯´
    -0.19
     addCriterion
    -0.18
    è¿Ļä¹Łæĺ¯
    -0.18
    è¿Ļåħ¶ä¸Ń
    -0.17
    åĽłä¸ºåľ¨
    -0.17
    ANA
    -0.16
    èĻ½çĦ¶
    -0.16
    è¿Ļå°±
    -0.16
    POSITIVE LOGITS
     ÐŁÐ¾Ñĩем
    0.25
    ouch
    0.20
    _b
    0.20
    _m
    0.19
     respective
    0.19
    “
    0.19
    åİŁæłĩé¢ĺ
    0.19
    ish
    0.19
    (s
    0.19
    _com
    0.18
    Activations Density 0.506%

    No Known Activations