© 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. 1021
    Prev
    Next
    INDEX
    Explanations

    area communication department

    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
    åıłåĬł
    -0.24
    人çļĦ
    -0.23
     outcomes
    -0.23
    .ZERO
    -0.21
     Contents
    -0.21
    çļĦä¸Ģç§į
    -0.21
     bá»ķ
    -0.21
    认
    -0.21
    人们çļĦ
    -0.21
     Ether
    -0.20
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.33
     quienes
    0.31
     grassroots
    0.28
    纷纷
    0.25
     dürfen
    0.24
     gotta
    0.24
    çĥŃæĥħ
    0.23
    were
    0.23
     fortunate
    0.23
     caravan
    0.23
    Activations Density 0.164%

    No Known Activations