© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 206
    Prev
    Next
    INDEX
    Explanations

    names of countries

    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
    Fax
    -0.26
    éĢŀ
    -0.25
    å¤§éĽ¨
    -0.24
    Leap
    -0.23
     acupuncture
    -0.23
     abortion
    -0.23
     fax
    -0.23
    owski
    -0.23
    oe
    -0.23
    åķ¡
    -0.22
    POSITIVE LOGITS
     Treasury
    0.27
     treasury
    0.26
    é¾Ħ
    0.25
    åİĨç¨ĭ
    0.23
     Kimber
    0.23
    ä¸įéĹ´æĸŃ
    0.23
    åĤ¨å¤ĩ
    0.23
    compiled
    0.23
     Guinness
    0.23
    è´®
    0.23
    Activations Density 0.005%

    No Known Activations