© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 855
    Prev
    Next
    INDEX
    Explanations

    Microsoft Azure services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    梧
    -0.24
    è¶ĭ
    -0.22
    æĭĺ
    -0.20
     wParam
    -0.20
     conferred
    -0.20
    squ
    -0.20
    å¦ĤæľŁ
    -0.20
    MeasureSpec
    -0.20
     angular
    -0.19
    ãģĵãģ¨
    -0.19
    POSITIVE LOGITS
     Separ
    0.28
    çķľç¦½
    0.22
    Separ
    0.22
    iddle
    0.22
    gers
    0.21
    åĪĨ离
    0.21
    tte
    0.20
    åIJĦèĩªçļĦ
    0.20
    otte
    0.20
    er
    0.20
    Activations Density 0.005%

    No Known Activations