© 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. 236
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No. B2

    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
    owing
    -0.26
    ãĥĬãĥ³
    -0.24
    ä¸Ĭåİ»
    -0.23
    ãģĿãģĵãģ§
    -0.23
    ằng
    -0.23
    ustom
    -0.22
    è¿ĽçIJĥ
    -0.22
    .pix
    -0.22
    Formats
    -0.22
    setter
    -0.21
    POSITIVE LOGITS
     ìĦ¤
    0.24
     Pry
    0.23
    _capacity
    0.22
    OrFail
    0.22
    å¹´ä¹ĭ
    0.22
    _CAPACITY
    0.22
    raq
    0.21
    ibly
    0.21
    åªĴ
    0.21
    åŁº
    0.21
    Activations Density 0.005%

    No Known Activations