© 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. 3255
    Prev
    Next
    INDEX
    Explanations

    close enough

    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
     WithEvents
    -0.29
    çĥĥ
    -0.24
    è·µ
    -0.23
    å¾Ĥ
    -0.23
    çĽ¸å¯¹æĿ¥è¯´
    -0.23
    æħ·
    -0.22
    oyer
    -0.22
     pragma
    -0.21
    æĢģ度
    -0.21
    lid
    -0.21
    POSITIVE LOGITS
     someday
    0.28
    åij½åIJį为
    0.26
     perfect
    0.24
    бо
    0.23
    Close
    0.23
    uvo
    0.23
    ç®Ģ称
    0.23
     cob
    0.22
    媲
    0.22
    ä¸ĭä¸Ģ个
    0.22
    Activations Density 0.045%

    No Known Activations