© 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. 16093
    Prev
    Next
    INDEX
    Explanations

    out of, off of, back into

    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
    å½ĵä¹ĭ
    -0.19
     additional
    -0.18
    _dec
    -0.18
    emet
    -0.18
    ç¿°
    -0.17
    èĵ¬
    -0.17
     обÑĢазом
    -0.17
    opard
    -0.17
    afil
    -0.16
    empor
    -0.16
    POSITIVE LOGITS
     Yourself
    0.20
    æĪij们çļĦ
    0.19
    æ¯ı个人çļĦ
    0.19
    æ¯ıä¸Ģä½į
    0.19
     mình
    0.18
    ä½łçļĦ
    0.18
    enson
    0.18
    æ¯ı个人
    0.18
    /from
    0.18
    çļĦ对象
    0.18
    Activations Density 0.055%

    No Known Activations