© 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. 14695
    Prev
    Next
    INDEX
    Explanations

    continuity and consistency

    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
    ãĤ»ãĥ«
    -0.20
    lights
    -0.20
    æĵħèĩª
    -0.19
    åħ¬éĸĭ
    -0.19
    erties
    -0.19
    ogl
    -0.18
    pixel
    -0.18
    intptr
    -0.18
    宿
    -0.18
     Butt
    -0.18
    POSITIVE LOGITS
     Caf
    0.18
    dorf
    0.18
     pres
    0.17
    beros
    0.17
    onium
    0.17
    åī©ä¸ĭçļĦ
    0.17
    groundColor
    0.17
    æĸ¹éĴĪ
    0.17
    åīįç½®
    0.16
    ilit
    0.16
    Activations Density 0.001%

    No Known Activations