© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1267
    Prev
    Next
    INDEX
    Explanations

    construction equipment

    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
    flux
    -0.27
     íĻĪ
    -0.24
     persecution
    -0.23
    çī¹æ´¾åijĺ
    -0.23
    å¥
    -0.23
    é¢ijçİĩ
    -0.23
     uncomp
    -0.22
    season
    -0.22
     unsub
    -0.22
    éħ¦
    -0.22
    POSITIVE LOGITS
    èµ·éĩįæľº
    0.40
    èµ·éĩį
    0.36
     crane
    0.35
    åĬ¨ä½ľ
    0.35
    åIJĬ
    0.35
    æĵįä½ľ
    0.33
     manoe
    0.32
     maneuver
    0.32
    é«ĺ空
    0.32
     operations
    0.31
    Activations Density 0.047%

    No Known Activations