© 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. 12604
    Prev
    Next
    INDEX
    Explanations

    living with family or host

    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
    èģļ
    -0.21
    磻
    -0.19
    æĺİæĺİ
    -0.19
    éĢīåĩº
    -0.19
    é½IJèģļ
    -0.18
    é¢ijçİĩ
    -0.18
    ipse
    -0.18
    é©»
    -0.18
    éĺIJéĩĬ
    -0.18
    irk
    -0.18
    POSITIVE LOGITS
    èµŀåĬ©
    0.22
     Sponsor
    0.21
     sponsor
    0.20
    让æĤ¨
    0.20
     sponsors
    0.20
     Overse
    0.19
    ponsor
    0.19
    -host
    0.19
    itti
    0.19
    Helpers
    0.19
    Activations Density 0.011%

    No Known Activations