© 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. 15927
    Prev
    Next
    INDEX
    Explanations

    thread / threaded

    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
    rait
    -0.19
    çĶŁç´ł
    -0.18
     Vend
    -0.18
    æĸ°éĻĪ代谢
    -0.18
    merc
    -0.17
    èݼ
    -0.17
    æľīä¸Ģ天
    -0.17
    ળ
    -0.17
    swap
    -0.17
    bor
    -0.17
    POSITIVE LOGITS
    éĻ©
    0.20
    QRST
    0.20
    ç¦ģåĮº
    0.19
    tti
    0.19
    éļľç¢į
    0.18
    alia
    0.17
    akedown
    0.17
    ÑĢÑĥб
    0.17
    cia
    0.17
    åİŁä»¶
    0.17
    Activations Density 0.003%

    No Known Activations