© 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. 16411
    Prev
    Next
    INDEX
    Explanations

    choice of

    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
    éĤ£ä»½
    -0.19
    ä»°
    -0.19
    ä»Ģä¹Īåij¢
    -0.19
    éĿĻéĿĻ
    -0.18
    è¯įæĿ¡
    -0.18
    csrf
    -0.18
    æł¹æį®ä¸įåIJĮ
    -0.18
    æ¡ij
    -0.17
    EGIN
    -0.17
    ARI
    -0.17
    POSITIVE LOGITS
     sorts
    0.18
    大èĤ¡ä¸ľ
    0.18
    yt
    0.18
    alcon
    0.17
     ust
    0.17
    otte
    0.17
    thon
    0.17
     sort
    0.17
     magnitude
    0.17
    minate
    0.17
    Activations Density 0.417%

    No Known Activations