© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 516
    Prev
    Next
    INDEX
    Explanations

    anionic / ionic / ion exchange / surfactants / lipid / conditioning

    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
     Dome
    -0.24
     dom
    -0.23
     Flight
    -0.23
    Chief
    -0.23
    失æݧ
    -0.22
     dome
    -0.22
     Heights
    -0.22
    è¡Įãģį
    -0.22
    BLE
    -0.22
    onen
    -0.22
    POSITIVE LOGITS
    åĮĸè¿Ľç¨ĭ
    0.28
    åĴĮ社ä¼ļ
    0.27
    inic
    0.24
    /social
    0.23
    çļĤ
    0.23
    èµ°ä¸Ĭ
    0.23
    åIJį称
    0.23
    ancode
    0.23
     inquire
    0.22
    åĮĸçļĦ
    0.22
    Activations Density 0.003%

    No Known Activations