© 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. 1659
    Prev
    Next
    INDEX
    Explanations

    measurement and diagnostic methods

    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
     empty
    -0.26
     adorned
    -0.26
     declared
    -0.25
     destinations
    -0.25
     untouched
    -0.25
     gracefully
    -0.24
     thunder
    -0.24
     slammed
    -0.24
     patron
    -0.24
    dest
    -0.24
    POSITIVE LOGITS
    çĽijæµĭ
    0.52
    æµĭéĩı
    0.48
    æµĭå®ļ
    0.47
    æ£Ģæµĭ
    0.46
     diagnostic
    0.46
     monitoring
    0.46
     measurement
    0.45
     measuring
    0.44
    è¯ĬæĸŃ
    0.43
    measurement
    0.42
    Activations Density 0.697%

    No Known Activations