© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12625
    Prev
    Next
    INDEX
    Explanations

    file formats and encoding

    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
    rier
    -0.22
    aise
    -0.20
    ÑģÑı
    -0.20
    åĴĮåľ°åĮº
    -0.20
    èħ¥
    -0.19
    geführt
    -0.19
    elfare
    -0.19
    ship
    -0.19
    ÑĮ
    -0.19
    _SDK
    -0.19
    POSITIVE LOGITS
    åĪ«äººçļĦ
    0.23
    ç«ĭåľº
    0.20
    immel
    0.18
    å°§
    0.17
     باÙĦÙĨ
    0.17
    å¤ĸéĿ¢
    0.17
    æĪIJ人
    0.17
    ç¿ģ
    0.17
    angers
    0.16
    OpenHelper
    0.16
    Activations Density 0.022%

    No Known Activations