© 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. 16589
    Prev
    Next
    INDEX
    Explanations

    URLs to code or websites

    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
    tá
    -0.20
    andi
    -0.20
    æ·Į
    -0.20
    /signup
    -0.19
    Government
    -0.19
     draped
    -0.19
    ioned
    -0.18
    ogie
    -0.18
    ç»Ĥ
    -0.18
    £¼
    -0.18
    POSITIVE LOGITS
    волÑĮ
    0.23
     ÅļwiÄĻt
    0.23
     amatør
    0.21
     mükem
    0.21
     Erotische
    0.20
     erotisk
    0.20
    åĩºäºİ
    0.20
     erotik
    0.20
     miÄĻd
    0.20
     fetisch
    0.20
    Activations Density 0.564%

    No Known Activations