© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15195
    Prev
    Next
    INDEX
    Explanations

    `to get`, `to lead`, `ball into`, `all relevant`, `in cranes`

    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
     cliff
    -0.22
    platform
    -0.19
    麻çĥ¦
    -0.18
    äºĨèµ·æĿ¥
    -0.18
    èµ·æĿ¥
    -0.17
     interchangeable
    -0.17
    åıijå¸ĥçļĦ
    -0.17
    çļĤ
    -0.17
    offline
    -0.17
    inction
    -0.17
    POSITIVE LOGITS
    å¯Įæ°ij
    0.22
    éļ°
    0.20
    åIJĮæĥħ
    0.20
     tả
    0.20
     ÑĨелÑĮ
    0.19
    çªľ
    0.19
    çIJ¦
    0.19
    åįıä½ľ
    0.19
    èµĤ
    0.19
    èİĨ
    0.19
    Activations Density 0.004%

    No Known Activations