© 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. 14035
    Prev
    Next
    INDEX
    Explanations

    credit / class / factors

    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
    ock
    -0.21
    _glob
    -0.20
    Off
    -0.20
    prise
    -0.20
    æħ¢æħ¢
    -0.19
    ever
    -0.19
     tit
    -0.19
    halt
    -0.19
    edia
    -0.18
    سر
    -0.18
    POSITIVE LOGITS
    /commons
    0.23
    æĺ¶
    0.22
    utters
    0.21
    楼ä¸Ĭ
    0.20
    åı°ä¸Ĭ
    0.19
    ä¿¡æģ¯æľįåĬ¡
    0.19
    èİ·èĥľ
    0.19
    /backend
    0.18
    Recorder
    0.18
    .Bean
    0.18
    Activations Density 0.011%

    No Known Activations