© 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. 2273
    Prev
    Next
    INDEX
    Explanations

    authoritarian clauses laws

    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
    缸éģĩ
    -0.27
    仡
    -0.27
    ç»Ĩå¿ĥ
    -0.25
    èĽŁ
    -0.24
    çĶ¨åĵģ
    -0.24
    stud
    -0.24
    交æį¢
    -0.23
     Havana
    -0.23
     McL
    -0.22
     reconciliation
    -0.22
    POSITIVE LOGITS
    模ç³Ĭ
    0.31
    æīĭ段
    0.31
    æĿ¡æ¬¾
    0.31
    clause
    0.31
    éļıæĦı
    0.30
     authoritarian
    0.28
    çģµæ´»æĢ§
    0.28
    è½»æĺĵ
    0.27
     clause
    0.27
     clauses
    0.27
    Activations Density 0.074%

    No Known Activations