© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3328
    Prev
    Next
    INDEX
    Explanations

    containing

    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
    Negative Logits
    erville
    -0.23
    åħ¶ä½Ļ
    -0.23
    mods
    -0.22
    èĦ±
    -0.22
    âĸĪâĸĪâĸĪâĸĪ
    -0.21
    unts
    -0.21
    +N
    -0.21
    NL
    -0.21
     ref
    -0.20
    +c
    -0.20
    POSITIVE LOGITS
    称ä¹ĭ
    0.25
    -containing
    0.24
    ooth
    0.23
    ä¼ĹæīĢ
    0.22
    æµĶ
    0.22
    éĺħ读åħ¨æĸĩ
    0.22
    çŁ¿å±±
    0.22
    é£
    0.22
    æ°ijæ£Ģå¯ŁéĻ¢
    0.22
     containing
    0.21
    Activations Density 0.267%

    No Known Activations