© 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. 1524
    Prev
    Next
    INDEX
    Explanations

    by reference

    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
     suger
    -0.27
    aget
    -0.26
    venge
    -0.25
    SHIFT
    -0.24
    æĪIJåĬŁçİĩ
    -0.24
     ÑĢеж
    -0.24
    feedback
    -0.24
    èĨ³
    -0.23
    -feed
    -0.23
    ProgressBar
    -0.23
    POSITIVE LOGITS
     referenced
    0.45
    çĶŁæķĪ
    0.42
    声æĺİ
    0.38
    失æķĪ
    0.38
     reference
    0.36
    å¼ķçĶ¨
    0.36
    宣
    0.36
     referencing
    0.36
     declared
    0.35
     automatically
    0.35
    Activations Density 0.299%

    No Known Activations