© 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. 11473
    Prev
    Next
    INDEX
    Explanations

    special characters followed by dates or names

    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
    op
    -0.21
     extra
    -0.21
    åĬł
    -0.21
    T
    -0.20
    oku
    -0.20
    ¼
    -0.19
     dip
    -0.19
    ack
    -0.19
    lit
    -0.19
    ä¾Ŀ
    -0.19
    POSITIVE LOGITS
    	TokenName
    0.23
    enez
    0.20
    åĮĸè¿Ľç¨ĭ
    0.19
    umont
    0.19
    _^(
    0.19
    'gc
    0.19
    èģ¯åIJĪ
    0.19
    >manual
    0.18
    ä¸ĢåĪĻ
    0.18
    æĿ¡è¯Ħ论
    0.18
    Activations Density 0.005%

    No Known Activations