© 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. 1035
    Prev
    Next
    INDEX
    Explanations

    window or tab

    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
     routines
    -0.23
    udio
    -0.21
     center
    -0.21
    izin
    -0.21
     batt
    -0.21
    ela
    -0.21
     systemd
    -0.21
    æīĢåľ¨
    -0.20
     routine
    -0.20
    ime
    -0.20
    POSITIVE LOGITS
    /process
    0.29
    /tab
    0.27
    (handles
    0.25
    /items
    0.24
    æĪĸå¤ļ
    0.24
    /thread
    0.24
    åŃIJéĩĮ
    0.23
    è°ģçŁ¥éģĵ
    0.23
    sheet
    0.23
    /event
    0.23
    Activations Density 0.037%

    No Known Activations