© 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. 13822
    Prev
    Next
    INDEX
    Explanations

    gem, color, layers, quality

    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¤ĸåĩº
    -0.23
    calar
    -0.22
    verbs
    -0.20
    é¦Ī
    -0.20
    第ä¸Ģ天
    -0.19
    âĬĭ
    -0.19
     twice
    -0.19
     peripheral
    -0.18
    oreach
    -0.18
    esium
    -0.18
    POSITIVE LOGITS
    è¯Ħ级
    0.37
    çŃī级
    0.34
    è´¨éĩıåĴĮ
    0.30
    è´¨éĩı
    0.28
    ä¼ĺè´¨
    0.25
    级åĪ«
    0.25
    顶级
    0.24
    åĪĨ级
    0.24
    quality
    0.24
    åĵģè´¨
    0.24
    Activations Density 0.010%

    No Known Activations