© 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. 11413
    Prev
    Next
    INDEX
    Explanations

    mountains and surrounding geography

    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
    èĬ¡
    -0.21
    ä¾®
    -0.21
    /il
    -0.20
    gefähr
    -0.20
    _sphere
    -0.19
    æµ·åºķ
    -0.19
    (DBG
    -0.19
    觥
    -0.18
    æĬĺ磨
    -0.18
    ỡ
    -0.18
    POSITIVE LOGITS
    è½®å»ĵ
    0.27
    åij¨è¾¹
    0.26
     skyline
    0.25
    èĥĮæĻ¯
    0.23
    åij¨åĽ´çļĦ
    0.23
    éĤ»
    0.23
    æĻ¯èī²
    0.22
    azy
    0.22
    éģĹ产
    0.22
     neighboring
    0.21
    Activations Density 0.023%

    No Known Activations