© 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. 1748
    Prev
    Next
    INDEX
    Explanations

    legal rights and privileges

    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
    精彩çļĦ
    -0.32
    (samples
    -0.27
    ç»ıéªĮ丰å¯Į
    -0.25
    PERT
    -0.25
     Vari
    -0.25
     Phaser
    -0.24
    æ·ĺæ±°
    -0.24
     Interval
    -0.24
     samples
    -0.24
    é«ĺæīĭ
    -0.24
    POSITIVE LOGITS
     privileges
    0.40
    å¾ħéģĩ
    0.40
     rights
    0.38
     protections
    0.37
     citizenship
    0.35
    身份
    0.34
    åľ°ä½į
    0.33
     nationality
    0.30
    rights
    0.30
     legal
    0.30
    Activations Density 0.027%

    No Known Activations