© 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. 2194
    Prev
    Next
    INDEX
    Explanations

    web urls and file paths

    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
     amount
    -0.24
    edly
    -0.24
     decre
    -0.24
    itial
    -0.23
    èĩªå¦Ĥ
    -0.22
     dw
    -0.22
     immediate
    -0.22
    edere
    -0.21
     decor
    -0.21
     trapped
    -0.21
    POSITIVE LOGITS
    shelf
    0.24
     Maid
    0.23
    åįĸåĩº
    0.23
    sales
    0.23
    geo
    0.22
    çŁ¿æ³īæ°´
    0.22
    south
    0.22
    (DBG
    0.21
    ä¸ĵä¸ļçļĦ
    0.21
    oauth
    0.21
    Activations Density 0.001%

    No Known Activations