© 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. 12070
    Prev
    Next
    INDEX
    Explanations

    -esia, -iana, -ian, -anese, -onesian

    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
    éĻµ
    -0.21
    æł·åŃIJ
    -0.19
    è¾ĺ
    -0.18
    å¹²èĦĨ
    -0.18
    aleb
    -0.17
    -rule
    -0.17
    å¿ĥ缮
    -0.17
    æģ¤
    -0.17
    è¥Ħ
    -0.17
    åĩ»
    -0.17
    POSITIVE LOGITS
    ened
    0.20
    runner
    0.20
    bart
    0.20
    忤
    0.20
    ocard
    0.19
    lund
    0.19
    inery
    0.19
    koa
    0.18
     Plat
    0.18
     Pager
    0.18
    Activations Density 0.003%

    No Known Activations