© 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. 510
    Prev
    Next
    INDEX
    Explanations

    secret agent, spy, or 007

    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¬ŀ
    -0.28
     mái
    -0.26
     Hearth
    -0.25
    寺åºĻ
    -0.24
    oker
    -0.23
     roof
    -0.23
    çī¦
    -0.23
     slab
    -0.22
    cms
    -0.22
     gens
    -0.22
    POSITIVE LOGITS
    è°į
    0.51
     espionage
    0.40
     spy
    0.40
     spies
    0.37
    çī¹æ´¾åijĺ
    0.34
     agent
    0.32
     CIA
    0.30
    agent
    0.30
    Spy
    0.30
    Agent
    0.29
    Activations Density 0.030%

    No Known Activations