© 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. 15946
    Prev
    Next
    INDEX
    Explanations

    events followed by time

    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
     Bes
    -0.20
    PropertyParams
    -0.18
    åIJĮåŁİ
    -0.18
     loạt
    -0.18
    rella
    -0.18
     horns
    -0.18
     '{@
    -0.18
    ÑĢаб
    -0.18
    èĮĥ
    -0.17
    缼ä¸ĸ
    -0.17
    POSITIVE LOGITS
    ographers
    0.20
    åijµ
    0.19
     Hoy
    0.19
    ographer
    0.19
    itra
    0.19
    åıijæĮ¥ä½ľçĶ¨
    0.19
    [::-
    0.19
    **↵
    0.19
    lobe
    0.18
     *[
    0.18
    Activations Density 0.117%

    No Known Activations