© 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. 14237
    Prev
    Next
    INDEX
    Explanations

    financial spending borrowing limits

    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¸Ĥåľºç«ŀäºī
    -0.21
    æĹłæīĢè°ĵ
    -0.20
     dap
    -0.20
    psilon
    -0.20
    æ¡£
    -0.19
    æ·±çŁ¥
    -0.19
    路线
    -0.19
    å¥ijæľº
    -0.19
    æŀģ端
    -0.19
    空çĻ½
    -0.19
    POSITIVE LOGITS
     limits
    0.24
     borrowing
    0.24
    éĢ¾
    0.22
     borrowed
    0.22
    ç»ĻåĪ«äºº
    0.21
    éĻIJéĩı
    0.21
    /template
    0.20
    borrow
    0.20
     sustain
    0.20
     exceed
    0.19
    Activations Density 0.033%

    No Known Activations