© 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. 12191
    Prev
    Next
    INDEX
    Explanations

    woodland, forest, trees, brush, woods

    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
    porto
    -0.23
    éĵĽ
    -0.21
     Desk
    -0.20
    åIJĮåŁİ
    -0.19
    èĪ¶
    -0.19
    趸
    -0.19
     Islanders
    -0.19
    traits
    -0.18
    Traits
    -0.18
    portrait
    -0.18
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.35
    è¦ĨçĽĸçİĩ
    0.27
    æłijæľ¨
    0.27
    森æŀĹ
    0.27
     forest
    0.24
    èĶ½
    0.24
     woods
    0.24
    æľ¨
    0.23
     trees
    0.23
     forests
    0.23
    Activations Density 0.037%

    No Known Activations