© 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. 16030
    Prev
    Next
    INDEX
    Explanations

    potatohead, spaghetti, butter cup pies

    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
     Bowling
    -0.22
     Tatto
    -0.21
    æ¤įæłij
    -0.20
     Impl
    -0.20
    æĢł
    -0.19
     Floral
    -0.19
    ipur
    -0.19
     Brewing
    -0.19
     Toys
    -0.18
    uche
    -0.18
    POSITIVE LOGITS
    æ±ģ
    0.21
    CVE
    0.20
    代è¨Ģ
    0.19
    åĻİ
    0.19
    çĨŁ
    0.19
    pan
    0.19
    è±ĨèħIJ
    0.19
    é¦ħ
    0.19
    èĽĭ
    0.19
    é¥Ńèıľ
    0.19
    Activations Density 0.107%

    No Known Activations