© 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. 11445
    Prev
    Next
    INDEX
    Explanations

    require('./toString')

    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£ij
    -0.17
    ermen
    -0.15
    lder
    -0.15
    ãģĹãĤĩãģĨ
    -0.15
    lier
    -0.14
    Ùģر
    -0.14
    _WEB
    -0.14
     Soros
    -0.14
    ness
    -0.14
    -caret
    -0.14
    POSITIVE LOGITS
    "%
    0.18
    >`
    0.17
    isateur
    0.17
    :`
    0.16
    =`
    0.16
    >`↵
    0.15
     bè
    0.15
    åı¯æĥ³
    0.15
    æĪij们
    0.15
    üns
    0.15
    Activations Density 0.158%

    No Known Activations