© 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. 13414
    Prev
    Next
    INDEX
    Explanations

    JBL Clip/Echo/Dot, HyperX Cloud, Waves, Namecoin

    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
    composite
    -0.21
    è¡·å¿ĥ
    -0.19
    ahas
    -0.19
    leo
    -0.18
    èĦļä¸ĭ
    -0.18
    vrier
    -0.18
    åĽŃ
    -0.18
    糧
    -0.18
    æģ³
    -0.18
    REA
    -0.18
    POSITIVE LOGITS
    ounces
    0.22
     branding
    0.21
     products
    0.20
    åĻ¨æĿIJ
    0.19
     logo
    0.19
    æĶ¶è´Ń
    0.19
    åIJ¸
    0.18
    åĵģçīĮ
    0.18
    èĢ³
    0.18
    ounce
    0.18
    Activations Density 0.005%

    No Known Activations