© 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. 1835
    Prev
    Next
    INDEX
    Explanations

    previews and anticipation

    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
    nah
    -0.23
     Platt
    -0.22
    ModelProperty
    -0.21
    ç°Į
    -0.21
    aber
    -0.21
    Preference
    -0.21
    æĪIJ为ä¸ŃåĽ½
    -0.21
    å¼¼
    -0.21
     tat
    -0.21
    ,lat
    -0.21
    POSITIVE LOGITS
    é¢ĦåijĬ
    0.57
     preliminary
    0.46
     preview
    0.46
     promise
    0.44
     Preview
    0.43
     previews
    0.43
     anticipation
    0.42
    -preview
    0.42
    é¢ĦåħĪ
    0.42
     anticipated
    0.41
    Activations Density 0.264%

    No Known Activations