© 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. 11248
    Prev
    Next
    INDEX
    Explanations

    sell something

    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
    å¯Ŀ
    -0.24
    criptor
    -0.21
    ãģĸ
    -0.19
    .Nav
    -0.19
    讵
    -0.19
    anzi
    -0.19
    interop
    -0.18
     заÑĤ
    -0.18
    antic
    -0.18
     Rav
    -0.18
    POSITIVE LOGITS
    稳妥
    0.21
    åİŁåĪĻ
    0.20
    ulers
    0.20
    å¦Ĥæľīä¾µæĿĥ
    0.20
    亲åıĭ
    0.20
    å·¥åĮł
    0.20
    è·ij
    0.19
    flare
    0.19
     ace
    0.19
     lan
    0.19
    Activations Density 0.624%

    No Known Activations