© 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. 15352
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations

    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
    é²ľè¡Ģ
    -0.20
    åı¤åŁİ
    -0.20
    umbo
    -0.19
    cran
    -0.19
    èĪĴæľį
    -0.19
    éĤ£è¾¹
    -0.18
    ç»ıéªĮåĢ¼
    -0.18
    å´®
    -0.18
    Ĭ¶
    -0.18
    gre
    -0.18
    POSITIVE LOGITS
    [__
    0.23
     Pulitzer
    0.20
    Israel
    0.20
    ANTA
    0.19
    è··
    0.18
    qd
    0.18
    createElement
    0.18
    .yahoo
    0.18
    /mit
    0.18
    setName
    0.18
    Activations Density 0.032%

    No Known Activations