© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2255
    Prev
    Next
    INDEX
    Explanations

    team and offensive performance

    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
    èµ
    -0.25
     paternal
    -0.24
    _den
    -0.22
    ä¸ļ绩
    -0.22
    (#)
    -0.22
    æľīæľŁ
    -0.22
     grandfather
    -0.22
    _INPUT
    -0.22
    èĢģ人家
    -0.21
    èIJ¥åĪ©
    -0.21
    POSITIVE LOGITS
    éĺŁåijĺ
    0.34
    éĽĨä½ĵ
    0.32
    éĺŁ
    0.32
    é»ĺå¥ij
    0.32
     teamwork
    0.30
     collective
    0.29
    åIJĪåĬĽ
    0.29
     team
    0.29
    éļĬ
    0.28
    åĽ¢éĺŁ
    0.28
    Activations Density 0.015%

    No Known Activations