© 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. 15990
    Prev
    Next
    INDEX
    Explanations

    refrigeration and freezing appliances

    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
    èĥ³
    -0.23
     Umb
    -0.20
    令çīĮ
    -0.19
     diam
    -0.19
    æŁĦ
    -0.19
    obil
    -0.19
     Sands
    -0.19
    _TYPEDEF
    -0.18
    oco
    -0.18
    .Token
    -0.18
    POSITIVE LOGITS
    åĨ·èĹı
    0.31
    åĪ¶åĨ·
    0.26
    åĨ°ç®±
    0.25
    åĪĨåĮº
    0.25
    æŃ»è§Ĵ
    0.25
     refriger
    0.23
    温度
    0.23
    空éĹ´
    0.22
    é£Łåĵģ
    0.22
    åĤ¨åŃĺ
    0.22
    Activations Density 0.014%

    No Known Activations