© 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. 16770
    Prev
    Next
    INDEX
    Explanations

    satire, parody, and comedy content

    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
    iate
    -0.21
     Legacy
    -0.20
    ottie
    -0.20
     legacy
    -0.18
    peg
    -0.18
    Legacy
    -0.18
     sol
    -0.18
    æĸĽ
    -0.18
     Calling
    -0.17
    èį¡
    -0.17
    POSITIVE LOGITS
    TH
    0.20
    strup
    0.20
    str
    0.20
    çļĦä¸ĢéĿ¢
    0.20
    俱
    0.19
    ç¿»
    0.19
    äºĭä¸ļåıijå±ķ
    0.19
    èµı
    0.18
    éªij
    0.18
    store
    0.18
    Activations Density 0.007%

    No Known Activations