© 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. 13935
    Prev
    Next
    INDEX
    Explanations

    run build, ViewModel Base, Forest Classifier, ng serve, Click Plus, as fast, level +, Horizon Marine, Address .G, _construct t

    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
    åıĪ好
    -0.21
    妣
    -0.19
    ä¸įæķ¢
    -0.19
     spoiler
    -0.18
    éĥ½ä¸įæķ¢
    -0.18
    å®ħ
    -0.18
    edBy
    -0.18
    对çŃĸ
    -0.18
    atron
    -0.17
     ÑĪколÑĮ
    -0.17
    POSITIVE LOGITS
    åħĪåīį
    0.23
     earlier
    0.21
    åľ¨æѤä¹ĭåīį
    0.20
    åįģåĪĨéĩįè¦ģ
    0.20
     Literal
    0.20
    åįģåĪĨ
    0.20
     ×ŀ×ŀש
    0.19
     Arcade
    0.19
     Earlier
    0.19
     Regel
    0.19
    Activations Density 0.629%

    No Known Activations