© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 284
    Prev
    Next
    INDEX
    Explanations

    costs and consequences

    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
    _COMPAT
    -0.25
    éĢıæĺİ
    -0.24
    ç²¾çĽĬæ±Ĥç²¾
    -0.24
    è¿ĩ渡
    -0.22
     Transparency
    -0.22
    /frontend
    -0.22
     transparency
    -0.22
     architects
    -0.22
    ä¸į足以
    -0.22
    å®ĮæĪIJäºĨ
    -0.21
    POSITIVE LOGITS
    åIJİæŀľ
    0.32
     consequences
    0.29
    æįŁå¤±
    0.29
    ç»ıæµİæįŁå¤±
    0.28
     :(
    0.27
    èµĶä»ĺ
    0.26
    èµĶåģ¿
    0.25
    LOSS
    0.25
     consequence
    0.25
    æĩĬ
    0.24
    Activations Density 0.168%

    No Known Activations