© 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. 14156
    Prev
    Next
    INDEX
    Explanations

    weapon accessories

    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
    _DISPATCH
    -0.22
     Gam
    -0.19
    åħīè¾ī
    -0.18
     Garn
    -0.18
    èĨı
    -0.18
    ieties
    -0.18
    å·¥ä½ľç«Ļ
    -0.18
    殿åłĤ
    -0.17
    èħ¥
    -0.17
     consc
    -0.17
    POSITIVE LOGITS
    åħµé©¬
    0.21
    饱满
    0.19
    åĨħçļĦ
    0.19
    uchos
    0.18
    éĺŁä¼į
    0.18
     holding
    0.18
    ä¼ĺåĮĸ
    0.18
     билеÑĤ
    0.18
    åĨĽéĺŁ
    0.17
    åĤ¨å¤ĩ
    0.17
    Activations Density 0.005%

    No Known Activations