© 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. 16526
    Prev
    Next
    INDEX
    Explanations

    blend of

    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
    ä»Ģä¹Īåij¢
    -0.22
    allis
    -0.18
     váºŃy
    -0.17
    æł·çļĦ
    -0.16
    å·¥åľ°
    -0.16
    çiler
    -0.15
    ä½Ĩä¸įéĻIJäºİ
    -0.15
    elmet
    -0.15
    dat
    -0.15
    ÃŃd
    -0.15
    POSITIVE LOGITS
    t
    0.19
    åľ¨ä¸Ģèµ·
    0.19
    tures
    0.19
    stone
    0.18
    stones
    0.18
    baugh
    0.18
    ancing
    0.18
    dings
    0.17
    lyph
    0.16
    quist
    0.16
    Activations Density 0.005%

    No Known Activations