© 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. 17248
    Prev
    Next
    INDEX
    Explanations

    damn it, shit, gosh-darndest, goddamn

    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
    Negative Logits
    å¥ĩèij©
    -0.21
    åĻ©
    -0.21
    abus
    -0.20
    èĿĮ
    -0.19
    æ®Ĭ
    -0.19
    unlikely
    -0.19
    å¾Īéĩįè¦ģçļĦ
    -0.19
    oret
    -0.19
    åĸ³
    -0.18
    åĪĹ为
    -0.18
    POSITIVE LOGITS
    verty
    0.20
    asaki
    0.20
    !
    0.19
    åĿļ强
    0.18
    adera
    0.18
    edo
    0.18
    å¥ĭè¿Ľ
    0.18
    è¦ģåĿļæĮģ
    0.17
    llib
    0.17
    ä¹Łè¦ģ
    0.17
    Activations Density 0.006%

    No Known Activations