© 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. 15549
    Prev
    Next
    INDEX
    Explanations

    audio components or technology

    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
    éķ¿å¾Ĺ
    -0.22
    arro
    -0.22
    ä½İ头
    -0.21
    æ¼Ķä¹ł
    -0.21
    åı£è¢ĭ
    -0.21
    åħ¬ä¸»
    -0.21
    èĭ±åĭĩ
    -0.20
    (iOS
    -0.20
    èĻļå¼±
    -0.20
    椰
    -0.20
    POSITIVE LOGITS
    溯æºIJ
    0.25
    å·¥ä½ľç«Ļ
    0.25
     vintage
    0.24
    纯
    0.22
     Pure
    0.22
     Watkins
    0.22
     pure
    0.21
    Pure
    0.21
     subrange
    0.21
     Listener
    0.21
    Activations Density 0.026%

    No Known Activations