© 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. 14863
    Prev
    Next
    INDEX
    Explanations

    budget, appropriation, proposal, schedules

    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
    åĸ·
    -0.22
     jet
    -0.21
    æĶ¶èİ·
    -0.20
    æIJŃ
    -0.20
    jet
    -0.20
    æīĭç»Ńè´¹
    -0.20
    _iso
    -0.20
    æݥ触
    -0.20
     конÑĤакÑĤ
    -0.19
    од
    -0.19
    POSITIVE LOGITS
    é¢Ħç®Ĺ
    0.38
     budget
    0.29
    udget
    0.29
     Budget
    0.28
    æĺİå¹´
    0.27
     budgets
    0.26
    budget
    0.26
    年度
    0.25
    ä»Ĭå¹´
    0.25
    ç¼ĸåĪ¶
    0.24
    Activations Density 0.026%

    No Known Activations