© 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. 16169
    Prev
    Next
    INDEX
    Explanations

    company names and types

    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
    该éĻ¢
    -0.21
    emens
    -0.20
    éĢĽè¡Ĺ
    -0.20
     пÑĢÑı
    -0.19
    oscope
    -0.18
    uber
    -0.18
    åĴ£
    -0.18
    沫
    -0.18
    çĬĢ
    -0.18
    ê³Ħ
    -0.17
    POSITIVE LOGITS
    nika
    0.20
    éĩİçĶŁ
    0.18
    åĤ¬
    0.18
    æĺ¯ä¸Ģ家
    0.18
     Hut
    0.17
    è¿Ļ家åħ¬åı¸
    0.17
    OLVE
    0.17
    æĺ¯æĪij
    0.17
    æľīéĻIJåħ¬åı¸
    0.17
    hiếu
    0.17
    Activations Density 0.186%

    No Known Activations