© 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. 15356
    Prev
    Next
    INDEX
    Explanations

    letter sequences following common initials

    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
    mf
    -0.20
    vere
    -0.19
    reak
    -0.19
    #:
    -0.18
    VP
    -0.18
    éĤ£æł·
    -0.18
    ROTO
    -0.18
    ç½®
    -0.18
    .isChecked
    -0.18
     aust
    -0.18
    POSITIVE LOGITS
    éłĺ
    0.25
    å©į
    0.23
    é¢Ĩ
    0.21
    èĬł
    0.21
    è°¢éŁµ
    0.20
    ä¿Ŀ驾æĬ¤
    0.20
    弸
    0.20
    为主è¦ģ
    0.19
    ä¸Ńåľº
    0.19
    使çĶ¨ç¶²è·¯
    0.19
    Activations Density 0.013%

    No Known Activations