© 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. 14541
    Prev
    Next
    INDEX
    Explanations

    license or copyright notices

    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
    被æįķ
    -0.17
     Archived
    -0.17
    subst
    -0.16
    åѵ
    -0.16
    icit
    -0.16
    @\
    -0.15
    /from
    -0.15
    tap
    -0.15
    太快
    -0.15
    好æ¶Īæģ¯
    -0.15
    POSITIVE LOGITS
     której
    0.21
    ä¹Łå°±æĺ¯
    0.20
     że
    0.20
     którym
    0.20
    æĪĸèĢħæĺ¯
    0.20
     których
    0.20
     którego
    0.19
     коÑĤоÑĢÑĭм
    0.18
     коÑĤоÑĢого
    0.18
     коÑĤоÑĢ
    0.17
    Activations Density 2.109%

    No Known Activations