© 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. 14754
    Prev
    Next
    INDEX
    Explanations

    viewing/opening/rendering documents

    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
    è°ļ
    -0.20
    .lift
    -0.19
    rá
    -0.18
    å¯Įæ°ij
    -0.18
     Morales
    -0.18
    eteria
    -0.18
     rad
    -0.18
     кл
    -0.17
     ce
    -0.17
     Getty
    -0.17
    POSITIVE LOGITS
    åijĪçİ°
    0.28
    Showing
    0.27
    å±ķ示
    0.27
    preview
    0.25
     пÑĢоÑģмоÑĤÑĢ
    0.23
     preview
    0.23
    欣èµı
    0.23
    åijĪçı¾
    0.23
    游è§Ī
    0.23
    æµıè§Ī
    0.23
    Activations Density 0.129%

    No Known Activations