© 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. 3326
    Prev
    Next
    INDEX
    Explanations

    location context

    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
     intrinsic
    -0.23
    cascade
    -0.23
     inherent
    -0.23
    eof
    -0.23
    åĶĩ
    -0.22
     Jackie
    -0.22
     glGen
    -0.22
    å¤įåĪ¶
    -0.21
     newSize
    -0.21
     Twice
    -0.21
    POSITIVE LOGITS
    æѤæŶ
    0.35
     whereabouts
    0.35
    æѤåĪ»
    0.33
    /activity
    0.33
    å¤Ħäºİ
    0.33
    åľ°çĤ¹
    0.30
    æѤæĻĤ
    0.29
     location
    0.29
    è¿Ļ个æŶåĢĻ
    0.29
    æŃ£å¤Ħäºİ
    0.29
    Activations Density 0.053%

    No Known Activations