© 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. 14524
    Prev
    Next
    INDEX
    Explanations

    cartoon related concepts

    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
    noch
    -0.20
    ðŁı»
    -0.19
    -0.19
    apy
    -0.17
    èĨĽ
    -0.16
    tures
    -0.16
    nahme
    -0.16
    orse
    -0.16
    gars
    -0.16
    imir
    -0.16
    POSITIVE LOGITS
    ish
    0.27
    ishly
    0.23
     пÑĢоиÑģ
    0.20
    eer
    0.20
    ing
    0.20
    izer
    0.20
    åĮĸçļĦ
    0.20
    ¿
    0.20
    ists
    0.19
    son
    0.19
    Activations Density 0.003%

    No Known Activations