© 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. 12001
    Prev
    Next
    INDEX
    Explanations

    landscapes, scenes, and backgrounds

    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
    æĺİç¡®è§Ħå®ļ
    -0.19
    buzz
    -0.18
    _virtual
    -0.18
    èĬ±çĵ£
    -0.17
    affer
    -0.17
     Moves
    -0.17
    æĬĹåĩ»
    -0.17
    illance
    -0.17
    åŃĿ
    -0.17
    usercontent
    -0.17
    POSITIVE LOGITS
    æĻ¯èī²
    0.27
    é£İæĻ¯
    0.25
    èĥĮæĻ¯
    0.23
     landscapes
    0.22
    æĦıå¢ĥ
    0.21
    åIJĮäºĭ们
    0.20
    山水
    0.20
    çĪ±å¥½èĢħ
    0.19
     backgrounds
    0.19
     backdrop
    0.19
    Activations Density 0.013%

    No Known Activations