© 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. 2128
    Prev
    Next
    INDEX
    Explanations

    memorandum of understanding or agreement

    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
    éĶ¤
    -0.23
    ANNOT
    -0.22
    æĺŁæľŁ
    -0.22
    .Comp
    -0.22
    ç²¾èĭ±
    -0.22
    ä½ľèĢħæľ¬äºº
    -0.22
    /errors
    -0.22
    ucas
    -0.22
    ä¸ĸä¸Ĭ
    -0.22
     Decomp
    -0.21
    POSITIVE LOGITS
     agreements
    0.33
    åIJĪä½ľåįıè®®
    0.32
     agreement
    0.31
     Agreement
    0.31
    åįıå®ļ
    0.29
    åįıè®®
    0.29
     UNESCO
    0.27
    (NS
    0.27
    æī¿è¯º
    0.26
    ç«łç¨ĭ
    0.25
    Activations Density 0.011%

    No Known Activations