© 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. 15547
    Prev
    Next
    INDEX
    Explanations

    in focus

    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
    aska
    -0.22
     Lowell
    -0.21
    é£İæľº
    -0.20
    æĮ¯å¥ĭ
    -0.20
    æ¿®
    -0.19
    çīĴ
    -0.19
    letters
    -0.19
    udent
    -0.19
     Propel
    -0.19
     Vulcan
    -0.19
    POSITIVE LOGITS
    çĶ»éĿ¢
    0.25
    æĭįæijĦ
    0.23
    çŀĦåĩĨ
    0.23
    ðŁĵ·
    0.23
    çľ¼çľĭ
    0.22
    éķľå¤´
    0.22
    æijĦå½±å¸Ī
    0.22
    Manual
    0.21
    _BITMAP
    0.21
    çľ¼
    0.21
    Activations Density 0.010%

    No Known Activations