© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 14660
    Prev
    Next
    INDEX
    Explanations

    government, America, Defendant rights

    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
    æ²Ļé¾Ļ
    -0.24
    æĺĩ
    -0.22
    åįĩ
    -0.21
    çİ°åľº
    -0.20
    ç¼¶
    -0.20
    çı¾åł´
    -0.20
    éģ½
    -0.18
    个人信æģ¯
    -0.18
    å®¶å±ħ
    -0.18
     Laud
    -0.18
    POSITIVE LOGITS
    åħľ
    0.28
    à¹Ģà¸Ńà¸ĩ
    0.25
     monopoly
    0.23
    åĩºæīĭ
    0.22
    åħ¬ç«ĭåĮ»éĻ¢
    0.22
     intervene
    0.22
    åĽ½æľī
    0.22
    CellValue
    0.22
    管çIJĨåijĺ
    0.21
    åĩºèµĦ
    0.21
    Activations Density 0.104%

    No Known Activations