© 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. 12065
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and names

    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
    istr
    -0.20
    èĦ±ç¦»
    -0.20
    åIJį声
    -0.20
    妨
    -0.20
    æ·¦
    -0.20
    çĩ®
    -0.20
    æĪIJåIJį
    -0.19
    橹
    -0.19
    aker
    -0.18
    idal
    -0.18
    POSITIVE LOGITS
    rees
    0.19
    jian
    0.18
    ä¸įåĩº
    0.18
    (DWORD
    0.18
     Champions
    0.18
    æµĭ
    0.18
    宿
    0.18
    æĺİå¹´
    0.17
     super
    0.17
    åĬł
    0.17
    Activations Density 0.017%

    No Known Activations