© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    fighter jets and carriers

    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
     descriptive
    -0.25
    ä¸įéĢļ
    -0.25
    æ´Ĺè¡£
    -0.25
    åľ°ä¸ĭ室
    -0.24
     Village
    -0.24
    éħµ
    -0.24
    æį»
    -0.23
     hostel
    -0.23
    <Item
    -0.23
    oga
    -0.23
    POSITIVE LOGITS
    æĪĺæľº
    0.47
    æĪĺæĸĹæľº
    0.46
     fighter
    0.40
     jets
    0.38
     fighters
    0.38
    é£ŀè¡Įåijĺ
    0.36
    éªģ
    0.35
     jet
    0.33
    fighter
    0.32
    çģ«ç®Ń
    0.31
    Activations Density 0.036%

    No Known Activations