© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 247
    Prev
    Next
    INDEX
    Explanations

    Department of

    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
     parentId
    -0.25
     sorts
    -0.24
     minor
    -0.23
     возмож
    -0.22
    çĶ¨å·¥
    -0.22
     Haupt
    -0.21
     substr
    -0.21
    Partial
    -0.21
    PerPage
    -0.20
    çİĭåŃIJ
    -0.20
    POSITIVE LOGITS
     Homeland
    0.28
     finance
    0.25
     federal
    0.25
    åľ¨è¿Ļæĸ¹éĿ¢
    0.25
     homeland
    0.24
     Justice
    0.23
     Sanders
    0.23
    èģĶéĤ¦
    0.23
    楣
    0.23
     Finance
    0.22
    Activations Density 0.014%

    No Known Activations