© 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. 3334
    Prev
    Next
    INDEX
    Explanations

    description

    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
     tang
    -0.25
     vice
    -0.24
    åıįä¹ĭ
    -0.23
    åľĪ
    -0.23
    Specifier
    -0.22
     Vice
    -0.22
     tangent
    -0.22
    atures
    -0.21
     worlds
    -0.21
    -boot
    -0.21
    POSITIVE LOGITS
    ï¼ļ↵
    0.35
    :↵
    0.32
    æ¦Ĥè¿°
    0.31
    å¦Ĥä¸ĭ
    0.31
    详æĥħ
    0.31
    æııè¿°
    0.30
    details
    0.28
    ï¼ļ↵↵
    0.28
    详ç»Ĩä»ĭç»į
    0.28
    :↵↵↵
    0.26
    Activations Density 0.234%

    No Known Activations