© 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. 11435
    Prev
    Next
    INDEX
    Explanations

    the color yellow

    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
    åĪ·åį¡
    -0.22
    RATION
    -0.21
    inker
    -0.21
    oice
    -0.20
    ORT
    -0.20
    åŃº
    -0.18
     Herman
    -0.18
    çݰ代åĮĸ
    -0.18
     Cros
    -0.18
    èİĬ
    -0.17
    POSITIVE LOGITS
    -yellow
    0.40
    é»Ħ
    0.33
    é»Ħèī²
    0.31
     yellow
    0.30
     Yellow
    0.30
    yellow
    0.30
    Yellow
    0.28
    é»ĥ
    0.27
    _yellow
    0.24
    YELLOW
    0.23
    Activations Density 0.084%

    No Known Activations