© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15237
    Prev
    Next
    INDEX
    Explanations

    wrecked, brand new, fog, touch

    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
     chance
    -0.20
    åĿļ
    -0.19
    /mod
    -0.19
    å·²ä¹ħçļĦ
    -0.19
    leÅŁme
    -0.19
    keiten
    -0.18
     opportunity
    -0.17
     Chad
    -0.17
    pora
    -0.17
    ijke
    -0.17
    POSITIVE LOGITS
    edBy
    0.29
    äºĨèµ·æĿ¥
    0.25
    èµ·æĿ¥
    0.22
    çŀ©çĽ®
    0.21
    äºĨä¸ĭæĿ¥
    0.20
    èµ·æĿ¥äºĨ
    0.20
    å¾Ĺå¾Ī
    0.20
    å¾Ĺä½ı
    0.20
    Indexes
    0.20
    EqualTo
    0.19
    Activations Density 0.347%

    No Known Activations