© 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. 16692
    Prev
    Next
    INDEX
    Explanations

    foreign language names and words

    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
    ISTA
    -0.21
    åħļåĨħ
    -0.19
    åĩĢåľŁ
    -0.19
     solid
    -0.18
    åħ¨å¤©
    -0.18
    åĮ¼
    -0.18
    ovsky
    -0.17
    å½ĸ
    -0.17
    aval
    -0.17
     radi
    -0.17
    POSITIVE LOGITS
    åĴĸ
    0.20
    Relation
    0.19
    è´¸
    0.19
    åĮĻ
    0.19
    æĨİ
    0.18
    ç«¥
    0.18
    éĽĩ
    0.18
    çĪµå£«
    0.18
    zet
    0.18
    дей
    0.18
    Activations Density 0.191%

    No Known Activations