© 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. 14691
    Prev
    Next
    INDEX
    Explanations

    provided or furnished

    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
     Hort
    -0.22
     trader
    -0.20
     trading
    -0.20
    apesh
    -0.19
    èIJ½åIJİ
    -0.18
    æ¯ĽåŃĶ
    -0.18
    forums
    -0.18
     traders
    -0.18
     BUY
    -0.18
    èĮ«çĦ¶
    -0.18
    POSITIVE LOGITS
    客人
    0.23
    èĩªå¸¦
    0.22
     guest
    0.22
    æłĩéħį
    0.21
    客
    0.21
    好è¯Ħ
    0.21
    Defaults
    0.21
    æıIJä¾ĽçļĦ
    0.20
    åŀ«
    0.20
    å·¾
    0.20
    Activations Density 0.014%

    No Known Activations