© 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. 12928
    Prev
    Next
    INDEX
    Explanations

    accordingly, duly, due

    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
    æĹłç©·
    -0.21
    常çĶ¨çļĦ
    -0.20
    æīĢæıIJä¾Ľ
    -0.19
    IBLE
    -0.19
    IRC
    -0.18
     bü
    -0.18
    rows
    -0.17
    æĹ¥å¸¸çĶŁæ´»
    -0.17
    ells
    -0.17
    EB
    -0.17
    POSITIVE LOGITS
     обÑĢазом
    0.27
    è°¨æħİ
    0.20
     Stam
    0.19
    /legal
    0.19
    æŶéĹ´åĨħ
    0.19
     manner
    0.18
    ivery
    0.18
    -paying
    0.17
    äºĭå®ľ
    0.17
    å°ıå¿ĥ
    0.17
    Activations Density 0.009%

    No Known Activations