© 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. 2535
    Prev
    Next
    INDEX
    Explanations

    country names or locations

    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
    æĤŃ
    -0.25
    zas
    -0.23
     localize
    -0.22
    lean
    -0.22
     cups
    -0.21
     лег
    -0.21
    anism
    -0.21
    翼
    -0.20
    诣
    -0.20
    -item
    -0.20
    POSITIVE LOGITS
     NPR
    0.27
    /Main
    0.25
    å¾ħ
    0.23
    HLT
    0.23
    带åĽŀ
    0.23
    è¿ľæ´ĭ
    0.23
    èµĦ产
    0.23
    硬
    0.22
    INTER
    0.22
     mirrors
    0.21
    Activations Density 0.256%

    No Known Activations