© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2750
    Prev
    Next
    INDEX
    Explanations

    famous directors and their works

    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
    åŁºæľ¬ä¿¡æģ¯
    -0.24
    åIJĦåįķä½į
    -0.24
    æĪĸå¤ļæĪĸå°ij
    -0.23
    æŨ
    -0.23
    åĪ°åºķ
    -0.23
    æĮģ
    -0.22
    究竣
    -0.22
     именно
    -0.22
    伸æīĭ
    -0.22
     ffi
    -0.22
    POSITIVE LOGITS
     previous
    0.31
     acclaimed
    0.29
     hyp
    0.29
    previous
    0.29
     blockbuster
    0.27
     successful
    0.26
     Hyp
    0.26
    ãĢĬ
    0.25
     famed
    0.25
     renowned
    0.25
    Activations Density 0.032%

    No Known Activations