© 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. 12770
    Prev
    Next
    INDEX
    Explanations

    camera -format

    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
    æģģ
    -0.21
    æİĪ
    -0.20
    Hon
    -0.20
    ç«ł
    -0.20
    åĮ¡
    -0.19
    Late
    -0.19
    raz
    -0.19
    Sheet
    -0.18
    NH
    -0.18
    ot
    -0.18
    POSITIVE LOGITS
    æİĤ
    0.21
    人èĦī
    0.19
    ç²¾è£ħ
    0.19
    edImage
    0.18
    就没æľī
    0.18
    éª
    0.18
    大巴
    0.17
    ãģ£ãģŁãĤī
    0.17
    _ghost
    0.17
    eneg
    0.17
    Activations Density 0.002%

    No Known Activations