© 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. 343
    Prev
    Next
    INDEX
    Explanations

    unlimited offers or discounts

    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
     debated
    -0.28
     largely
    -0.25
    herited
    -0.24
    andel
    -0.24
     imagined
    -0.24
     ultimately
    -0.23
    æķĻè®Ń
    -0.23
    ä¹ĭä½ľ
    -0.23
    次ä¼ļè®®
    -0.23
    åıijæĮ¥äºĨ
    -0.23
    POSITIVE LOGITS
    ä¼ĺæĥł
    0.42
    ç¦ıåĪ©
    0.37
     unlimited
    0.36
     Unlimited
    0.33
    å¥ĸåĬ±
    0.32
    ä¼ĺæĥłæĶ¿çŃĸ
    0.31
    åıªè¦ģä½ł
    0.31
    åıªéľĢ
    0.30
    åħįè´¹
    0.29
    åĬŀçIJĨ
    0.29
    Activations Density 0.031%

    No Known Activations