© 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. 16437
    Prev
    Next
    INDEX
    Explanations

    awards and certifications

    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
    eka
    -0.23
    é²ľ
    -0.22
    éĹ»
    -0.20
    macro
    -0.19
    èģŀ
    -0.19
     decks
    -0.19
    ä¸ŀ
    -0.18
    å·¥å§Ķ
    -0.18
     Discipline
    -0.18
    (ii
    -0.18
    POSITIVE LOGITS
    è¯Ħ级
    0.22
    乡æĿij
    0.19
    ognito
    0.19
    _plain
    0.18
    åĺī
    0.18
    粤
    0.18
    çĶ»åĥı
    0.18
    æıIJä¾ĽæĽ´å¤ļ
    0.18
    è¯Ħå®ļ
    0.18
    ç¦ħ
    0.18
    Activations Density 0.006%

    No Known Activations