© 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. 13254
    Prev
    Next
    INDEX
    Explanations

    reducing processing time or cost

    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
    å¾Ī好çļĦ
    -0.23
    éĿŀ常好çļĦ
    -0.23
    ä¸įåĪĨ
    -0.20
    ä¸įéĶĻçļĦ
    -0.20
    å¥ijæľº
    -0.20
    pector
    -0.20
    æŁIJç§į
    -0.20
    ople
    -0.20
    åĪ«è¯´
    -0.20
    /android
    -0.19
    POSITIVE LOGITS
    ä¸įå¿ħè¦ģçļĦ
    0.38
     unnecessary
    0.26
    overall
    0.24
    å°ij
    0.23
     overall
    0.23
    è´Łæĭħ
    0.22
    å°ijäºĨ
    0.22
     reliance
    0.22
    /no
    0.21
    Overall
    0.21
    Activations Density 0.183%

    No Known Activations