© 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. 16347
    Prev
    Next
    INDEX
    Explanations

    edited, edits, modifying, modified

    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
    RIA
    -0.20
    rido
    -0.19
     Rio
    -0.19
    ,),
    -0.19
    çľģå¸Ĥ
    -0.19
    ientes
    -0.18
    üs
    -0.18
    é»į
    -0.18
    ateg
    -0.18
    èĪĴ
    -0.18
    POSITIVE LOGITS
    好å¤ļ
    0.21
    çĽijäºĭä¼ļ
    0.20
    æľĪä¸ĭ
    0.20
    ä¿®æĶ¹
    0.20
    奶
    0.20
    礼è²Į
    0.20
    篡
    0.20
    ä¿®æŃ£
    0.19
    箨
    0.19
    ÑģÑĮ
    0.19
    Activations Density 0.002%

    No Known Activations