© 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. 15416
    Prev
    Next
    INDEX
    Explanations

    Schumacher, Schumaker, Schuurs

    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
    ly
    -0.21
    å£ķ
    -0.19
     grit
    -0.17
    ty
    -0.17
     ty
    -0.17
    å°±èĥ½å¤Ł
    -0.17
    tenant
    -0.17
    ness
    -0.17
    ä¹ĥ
    -0.17
    åĮĸè¿Ľç¨ĭ
    -0.17
    POSITIVE LOGITS
    olen
    0.20
    èĥ¼
    0.20
    olan
    0.20
    åIJ®
    0.19
     Covenant
    0.18
    /Foundation
    0.18
    åı¹äºĨ
    0.18
    Cancelable
    0.18
    å¤ĩåıĹ
    0.18
    cial
    0.17
    Activations Density 0.002%

    No Known Activations