© 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. 15065
    Prev
    Next
    INDEX
    Explanations

    digital media technologies or developments

    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
    amber
    -0.22
    æĸ§
    -0.22
    æľ¬ç«Ļ
    -0.21
    å°»
    -0.19
    placeholders
    -0.18
    å¼ķèµ·äºĨ
    -0.18
    çIJĨç§ij
    -0.18
    Ending
    -0.18
     sped
    -0.18
    .packet
    -0.18
    POSITIVE LOGITS
    ħ§
    0.20
    èĥª
    0.20
    -related
    0.20
     pal
    0.19
    åľ¨çĶŁæ´»ä¸Ń
    0.18
    utsch
    0.18
    åŃIJåŃĻ
    0.18
    /jav
    0.18
    ecret
    0.18
    cps
    0.17
    Activations Density 0.284%

    No Known Activations