© 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. 12453
    Prev
    Next
    INDEX
    Explanations

    wanted to create

    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
    çĽijåIJ¬é¡µéĿ¢
    -0.25
    	RTLR
    -0.24
    azzi
    -0.22
    ayar
    -0.22
    ilater
    -0.21
    illac
    -0.21
    éĨį
    -0.20
    amacare
    -0.20
    ileaks
    -0.20
    ivia
    -0.20
    POSITIVE LOGITS
    æĬĢæ³ķ
    0.34
    ä½ľåĵģ
    0.31
    åĪĽä½ľ
    0.30
    å®ĮæĪIJåIJİ
    0.29
    å®Įå·¥
    0.28
    æĿIJæĸĻ
    0.28
    æĸ°æīĭ
    0.27
    éľĢè¦ģçĶ¨åĪ°
    0.27
    åĬ¨æīĭ
    0.27
    æĪIJåĵģ
    0.27
    Activations Density 0.073%

    No Known Activations