© 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. 15063
    Prev
    Next
    INDEX
    Explanations

    Jack Nicklaus, Gap, shirts

    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
    æľĪä¸ĭ
    -0.21
    æ°ijéĸĵ
    -0.20
    _INITIALIZER
    -0.20
    æ°ijéĹ´
    -0.19
    天ä¸Ĭ
    -0.18
    æ°ijæĦı
    -0.18
    æ°ijå¿ĥ
    -0.18
    zahl
    -0.18
    éĿłè°±
    -0.18
    .animation
    -0.18
    POSITIVE LOGITS
    è¡£çī©
    0.19
     Jacqueline
    0.18
     Tib
    0.18
     Percy
    0.18
     shirts
    0.18
    é²į
    0.18
     Detect
    0.18
    èĸ°
    0.18
     shirt
    0.18
    åĮ¾
    0.18
    Activations Density 0.001%

    No Known Activations