© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17003
    Prev
    Next
    INDEX
    Explanations

    great-grandson or great-granddaughter

    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
    .$.
    -0.18
    	ASSERT
    -0.18
     Opp
    -0.17
    ROTO
    -0.17
    arov
    -0.17
    èµĥ
    -0.17
     Marshall
    -0.17
    梽
    -0.16
    æ¥ŀ
    -0.16
     Zwe
    -0.16
    POSITIVE LOGITS
    èĪĽ
    0.22
    俦
    0.21
    åł¡
    0.20
    son
    0.19
    bidden
    0.19
    å±Ģå±Ģéķ¿
    0.19
    人为
    0.18
    Misc
    0.18
    fon
    0.18
    ster
    0.18
    Activations Density 0.001%

    No Known Activations