© 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. 16245
    Prev
    Next
    INDEX
    Explanations

    URLs starting with http or https

    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
    VIC
    -0.19
    é¦Ĵ头
    -0.19
    ight
    -0.19
    (WIN
    -0.18
    hoff
    -0.18
    ä¹Ĥ
    -0.18
     trÆ°ng
    -0.18
    ä¸ŃåİŁ
    -0.17
     noqa
    -0.17
    ç¾
    -0.17
    POSITIVE LOGITS
    TING
    0.20
    毫ä¸į
    0.20
    meer
    0.19
    _audit
    0.18
    è¦ģåľ¨
    0.18
    inden
    0.18
    庶
    0.18
    æݨ
    0.18
    elaide
    0.17
    èĬĹ
    0.17
    Activations Density 0.021%

    No Known Activations