© 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. 15029
    Prev
    Next
    INDEX
    Explanations

    species suffixes -i or -ii

    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
    ä¸įçķĻ
    -0.21
     Goodman
    -0.20
    带走
    -0.20
    çĶ²éĨĽ
    -0.19
    èĢĹ
    -0.19
    Marsh
    -0.19
    ä¼Ļ
    -0.18
    ç¼ĸç»ĩ
    -0.18
    宿
    -0.18
    ä¼ģä¸ļ管çIJĨ
    -0.18
    POSITIVE LOGITS
    iances
    0.21
    eni
    0.21
    ensis
    0.20
    èĬĭ
    0.19
    iod
    0.19
    enie
    0.19
    koa
    0.19
    æĸĽ
    0.18
    specifier
    0.18
    icus
    0.18
    Activations Density 0.049%

    No Known Activations