© 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. 607
    Prev
    Next
    INDEX
    Explanations

    women

    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
    ä¹°åįķ
    -0.30
    æĶ¹ç¼ĸ
    -0.25
     material
    -0.24
    壮大
    -0.23
    material
    -0.22
    åľ°çĭ±
    -0.22
    æ¦ľ
    -0.22
    åIJ¸å¼ķ
    -0.22
     mater
    -0.21
     staff
    -0.21
    POSITIVE LOGITS
    æľĭåıĭ们
    0.27
    sWith
    0.26
    abouts
    0.25
    ilians
    0.23
     surveyed
    0.23
    _toolbar
    0.22
    åŁºæľ¬æĥħåĨµ
    0.22
    çŀ¿
    0.22
    /her
    0.21
    å©ļåIJİ
    0.21
    Activations Density 0.053%

    No Known Activations