© 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. 910
    Prev
    Next
    INDEX
    Explanations

    legal agreements and approvals

    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
    ç»ıéªĮåĴĮ
    -0.25
    çªĺ
    -0.25
    laden
    -0.24
    åı¯çĸij
    -0.24
     suspect
    -0.24
    ä½ľé£İ
    -0.24
    å·¥ä½ľç»ıéªĮ
    -0.24
    åįķ纯çļĦ
    -0.23
    éļı便
    -0.23
    nets
    -0.23
    POSITIVE LOGITS
    çĶŁæķĪ
    0.40
     finalized
    0.34
     unanimously
    0.33
     ratified
    0.31
     approved
    0.30
    æī¹åĩĨ
    0.30
    åIJĮæĦı
    0.29
    çŃĶåºĶ
    0.29
    éĩĩ纳
    0.28
    åħģ许
    0.28
    Activations Density 0.050%

    No Known Activations