© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 687
    Prev
    Next
    INDEX
    Explanations

    proposed versus debated

    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
    å·§å¦Ļ
    -0.31
    顺åĪ©å®ĮæĪIJ
    -0.29
    ä¸īæĿ¡
    -0.25
    éĢļçķħ
    -0.25
    .getProperties
    -0.23
     easiest
    -0.23
     fortunately
    -0.23
    åŁºæľ¬ä¿¡æģ¯
    -0.23
    ,err
    -0.23
    çķħéĢļ
    -0.23
    POSITIVE LOGITS
     controversial
    0.34
    ä¸»å¼ł
    0.30
    è¦ģä¸įè¦ģ
    0.30
     proposed
    0.30
    äºīè®®
    0.28
    äºī论
    0.28
     versus
    0.27
     argue
    0.27
     debated
    0.27
    isor
    0.27
    Activations Density 0.453%

    No Known Activations