© 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. 16697
    Prev
    Next
    INDEX
    Explanations

    expect variations

    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
    ä¸į失
    -0.20
    诰
    -0.19
     Klein
    -0.19
    ÑĢеги
    -0.18
    Ù¬
    -0.18
    çĻ½éĵ¶
    -0.18
    åħ±èµ¢
    -0.18
    hazi
    -0.18
    çļĦç«ŀäºī
    -0.18
    æŀŃ
    -0.17
    POSITIVE LOGITS
    å¦Ļ
    0.21
    è¿Ļè¯Ŀ
    0.18
     Outstanding
    0.18
    åĽ¿
    0.18
    çķ¸
    0.18
    ÑģÑĤÑĢа
    0.17
     lung
    0.17
     applicationContext
    0.17
    [:,
    0.17
     amusement
    0.17
    Activations Density 0.085%

    No Known Activations