© 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. 2471
    Prev
    Next
    INDEX
    Explanations

    gadgets and novelty items

    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
    eing
    -0.24
    é¢Ĩä¼ļ
    -0.21
    è¢Ĥ
    -0.20
    halt
    -0.20
    oce
    -0.19
     Cyril
    -0.19
     Pharmacy
    -0.19
    aal
    -0.19
     Alban
    -0.19
    addock
    -0.19
    POSITIVE LOGITS
     gadgets
    0.29
     gadget
    0.26
    çİ©æĦı
    0.26
     toys
    0.23
    è°ľ
    0.23
     surprise
    0.22
    ry
    0.22
    bat
    0.22
    å°ıäºĭ
    0.21
     hobbies
    0.21
    Activations Density 0.017%

    No Known Activations