© 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. 11034
    Prev
    Next
    INDEX
    Explanations

    CEO followed by title or role

    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
    ãģĹãģ¾ãģĨ
    -0.21
    lock
    -0.18
    locked
    -0.18
    lopen
    -0.17
    åīĤ
    -0.17
    measure
    -0.17
    elope
    -0.17
    å¢ī
    -0.17
    weise
    -0.17
    å¾Īæ·±
    -0.17
    POSITIVE LOGITS
    åħ¼
    0.23
    å¨ĺ
    0.22
    iling
    0.20
    /operator
    0.20
    ptions
    0.20
    ichel
    0.19
    åĬ©çIJĨ
    0.19
    æĹĹä¸ĭ
    0.18
    éĻĽä¸ĭ
    0.18
    éĿŀåĩ¡
    0.17
    Activations Density 0.007%

    No Known Activations