© 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. 10912
    Prev
    Next
    INDEX
    Explanations

    occurrences or counts

    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
    çķĮéĻIJ
    -0.19
    arn
    -0.18
    çIJĨäºĭ
    -0.18
    moment
    -0.17
     Günc
    -0.17
    transpose
    -0.17
    -ft
    -0.17
    TURE
    -0.17
    éĽª
    -0.17
     gravity
    -0.16
    POSITIVE LOGITS
    akis
    0.23
    æĸ°ä¸Ģè½®
    0.20
    èĵĵ
    0.18
    æŀ§
    0.17
    /generated
    0.17
    饮åĵģ
    0.17
    fä
    0.17
    è¾ĺ
    0.16
    åıĪä¸Ģ次
    0.16
    çŀĦ
    0.16
    Activations Density 0.002%

    No Known Activations