© 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. 2178
    Prev
    Next
    INDEX
    Explanations

    aviation speed

    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
    ÑĢÑĭ
    -0.23
    èµŃ
    -0.23
    rag
    -0.23
     Eternal
    -0.21
    ä½łçļĦ
    -0.20
    IAL
    -0.20
    goals
    -0.20
    è¿Ļç¬Ķ
    -0.20
    units
    -0.20
    人æ°ijæľįåĬ¡
    -0.20
    POSITIVE LOGITS
    ä¸Ńç¾İ
    0.23
    owns
    0.23
    ä¼ģä¸ļ
    0.23
    åħ¨åŁŁ
    0.23
    è¿·ä½ł
    0.22
    ablish
    0.22
     glob
    0.22
    åĪĽæĬķ
    0.22
    称
    0.22
    æľĢåIJİä¸Ģ次
    0.22
    Activations Density 0.002%

    No Known Activations