© 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. 15617
    Prev
    Next
    INDEX
    Explanations

    groundbreaking and cutting-edge research/technology

    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
    ings
    -0.22
    INGS
    -0.20
    åħ¬ç§¯éĩij
    -0.19
    èĤ©è´Ł
    -0.19
     dÃłng
    -0.18
    ãģ£ãģįãĤĬ
    -0.18
    ities
    -0.17
    æĪIJåijĺåĽ½
    -0.17
    éĺ¶æ®µæĢ§
    -0.16
    screen
    -0.16
    POSITIVE LOGITS
     Downing
    0.20
    ä¹ĭä½ľ
    0.19
     technology
    0.19
     discoveries
    0.18
     ideas
    0.18
     innov
    0.18
    -edge
    0.18
    åŀł
    0.17
    çļĦæĥ³æ³ķ
    0.17
    hip
    0.17
    Activations Density 0.010%

    No Known Activations