© 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. 12695
    Prev
    Next
    INDEX
    Explanations

    photograph and image contexts

    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
    第ä¸ĢèĬĤ
    -0.24
     GridLayout
    -0.19
    åį¦
    -0.18
    ofil
    -0.18
     effectively
    -0.18
    eldorf
    -0.18
    oton
    -0.17
    \Support
    -0.17
    æ«
    -0.17
    _customize
    -0.17
    POSITIVE LOGITS
    åĽ¾çīĩæĿ¥æºIJ
    0.33
    Courtesy
    0.31
     photo
    0.30
    .jpg
    0.28
    .JPG
    0.28
    çħ§çīĩ
    0.28
     Photo
    0.26
     Courtesy
    0.26
    åĽ¾ä¸º
    0.26
     photograph
    0.25
    Activations Density 0.143%

    No Known Activations