© 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. 3046
    Prev
    Next
    INDEX
    Explanations

    first step

    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
    ä¼´
    -0.26
    å°ij
    -0.24
    åħ±æľī
    -0.24
    ign
    -0.23
    è¿Ľåĩº
    -0.23
    _examples
    -0.23
    åħ±
    -0.23
    è¹Ĭ
    -0.23
    åıª
    -0.23
    çĶ¨äºĨ
    -0.23
    POSITIVE LOGITS
    åħĪæĬĬ
    0.36
    第ä¸ĢæŃ¥
    0.35
    é¦ĸåħĪè¦ģ
    0.32
     prerequisite
    0.30
    åħĪ
    0.30
    defs
    0.29
    äºĨ解ä¸Ģä¸ĭ
    0.29
    ç¡®ç«ĭ
    0.28
     foremost
    0.28
    åİĺ
    0.28
    Activations Density 0.074%

    No Known Activations