© 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. 15596
    Prev
    Next
    INDEX
    Explanations

    after_sign_in_path_for

    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
    oba
    -0.20
    kı
    -0.17
    èĵģ
    -0.17
    å°ıçĻ½
    -0.17
    icana
    -0.17
    ipi
    -0.17
    æ´§
    -0.17
    ä¸Ģ份
    -0.17
    éĶĢåĶ®æĶ¶åħ¥
    -0.16
    elines
    -0.16
    POSITIVE LOGITS
    hread
    0.20
    è®°å¾Ĺ
    0.19
    ['__
    0.18
    èĶĹ
    0.18
    å¾Ĵ
    0.18
    è¿Ļä¹Īåģļ
    0.18
    ãģ¾ãģĹãģ¦
    0.18
    çIJĨçĶ±
    0.18
    宿
    0.18
    ivas
    0.18
    Activations Density 0.004%

    No Known Activations