© 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. 13171
    Prev
    Next
    INDEX
    Explanations

    image rights, spa holidays, clinical trials

    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
     коÑĤоÑĢого
    -0.19
    åı¦ä¸ĢåįĬ
    -0.19
    第äºĮç§į
    -0.18
    æł¹æľ¬ä¸į
    -0.18
    第äºĮ个
    -0.18
    æ©Ħæ¦Ħ
    -0.17
    微信åı·
    -0.17
    嬬
    -0.17
    è²Įä¼¼
    -0.17
    大æ°Ķ
    -0.16
    POSITIVE LOGITS
    é¡ĺ
    0.18
    æ¯ģ
    0.18
    iris
    0.17
     dime
    0.17
    ä¸ĢèĪ¬
    0.17
    ãģ¾ãģĤ
    0.17
    clide
    0.17
    еÑĩно
    0.17
     telemetry
    0.16
    éĴ°
    0.16
    Activations Density 0.224%

    No Known Activations