© 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. 1383
    Prev
    Next
    INDEX
    Explanations

    greetings like "hi all" or "hello everyone"

    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
    ä¸İåħ¶ä»ĸ
    -0.24
    altitude
    -0.23
    è¡Įä¸ļçļĦ
    -0.23
    är
    -0.22
     altitude
    -0.22
    女åĦ¿
    -0.22
     disposable
    -0.21
    åIJįåı«
    -0.21
     himself
    -0.21
    aris
    -0.21
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.28
    ä¼Ļ
    0.24
    åĽ´
    0.24
    é½IJèģļ
    0.24
    åħ±åIJĮåĬªåĬĽ
    0.23
    members
    0.23
    åIJĦèĩª
    0.23
    äºijéĽĨ
    0.23
     gathered
    0.22
    .follow
    0.22
    Activations Density 0.045%

    No Known Activations