© 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. 12427
    Prev
    Next
    INDEX
    Explanations

    people names

    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·¥ä½ľç«Ļ
    -0.22
    空çĻ½
    -0.20
     imb
    -0.19
    &id
    -0.18
    _prot
    -0.18
    imb
    -0.18
    ç¹ĩ
    -0.18
    为大家
    -0.18
     Glob
    -0.18
    ReadStream
    -0.18
    POSITIVE LOGITS
    妨ç¢į
    0.24
     Haupt
    0.23
    两åIJį
    0.19
    æŃ£åĵģ
    0.18
    ä¼ģåĽ¾
    0.18
    anka
    0.18
    å°ijæķ°æ°ijæĹı
    0.18
    æ³ķåħ°
    0.18
    _CYCLE
    0.17
    å«ī
    0.17
    Activations Density 0.083%

    No Known Activations