© 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. 2422
    Prev
    Next
    INDEX
    Explanations

    suspension, halting, or pause

    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
     proportions
    -0.26
     seated
    -0.26
     Plain
    -0.26
     xy
    -0.24
     combined
    -0.24
     enough
    -0.23
     seating
    -0.23
    igsaw
    -0.23
     plain
    -0.23
    ational
    -0.22
    POSITIVE LOGITS
    æļĤåģľ
    0.53
    æļĤç¼ĵ
    0.52
    æļĤ
    0.42
    æļĤæŶ
    0.41
    æIJģ
    0.40
    æļ«
    0.37
     temporarily
    0.36
    åģľæŃ¢
    0.35
     indefinitely
    0.33
     suspend
    0.33
    Activations Density 0.048%

    No Known Activations