© 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. 3054
    Prev
    Next
    INDEX
    Explanations

    chase, pursuit, or fleeing

    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
    è¿ĩ渡
    -0.24
     graded
    -0.23
     reading
    -0.23
     Reading
    -0.22
    ä½łæĺ¯
    -0.22
    积æ·Ģ
    -0.22
    飬
    -0.21
    chalk
    -0.21
     Orientation
    -0.21
     slate
    -0.21
    POSITIVE LOGITS
    å¥Ķè·ij
    0.46
    追赶
    0.43
    éĢĥè·ij
    0.42
     chase
    0.39
    追éĢIJ
    0.39
     trailing
    0.38
    赶åĪ°
    0.38
    è·ij
    0.37
     fleeing
    0.35
     chased
    0.34
    Activations Density 0.031%

    No Known Activations