© 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. 11653
    Prev
    Next
    INDEX
    Explanations

    assessment and scoring

    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
    æ³ķå¾ĭ顾éĹ®
    -0.23
     bow
    -0.19
     DISPATCH
    -0.19
    æŀ§
    -0.18
     bows
    -0.18
    åĬŀå®ŀäºĭ
    -0.18
    idel
    -0.18
    olumes
    -0.17
    åľ¨çº¿åĴ¨è¯¢
    -0.17
    _STOCK
    -0.17
    POSITIVE LOGITS
    è¯ĦåĪĨ
    0.31
    åѦçĶŁçļĦ
    0.28
     scores
    0.25
     scoring
    0.25
    è¯Ħ
    0.25
    对åѦçĶŁ
    0.25
    (score
    0.23
     score
    0.23
     student
    0.23
    ç»ĨåĪĻ
    0.22
    Activations Density 0.045%

    No Known Activations