© 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. 15361
    Prev
    Next
    INDEX
    Explanations

    active/passive, absolute/relative, dynamic/static, explicit/implicit

    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
    é¼ĵ
    -0.20
    fortune
    -0.19
    eren
    -0.19
    椽
    -0.19
    Highlighted
    -0.19
    ä¸Ģç¬Ķ
    -0.18
    ÑĢей
    -0.17
    arie
    -0.17
    rots
    -0.17
    _FIND
    -0.17
    POSITIVE LOGITS
    isd
    0.22
    ä»Ģä¹ĪæĦıæĢĿ
    0.20
    çģ¯çģ«
    0.20
    èĵij
    0.19
    座
    0.18
    æĺī
    0.18
    æIJĶ
    0.18
    çļĦåĮºåĪ«
    0.18
    çļĦåħ³ç³»
    0.18
    æ©IJ
    0.18
    Activations Density 0.109%

    No Known Activations