© 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. 768
    Prev
    Next
    INDEX
    Explanations

    license specifications

    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
    iblings
    -0.27
    verted
    -0.24
    cka
    -0.24
     culturally
    -0.23
    éģ¥è¿ľ
    -0.22
    hec
    -0.22
    æľĭåıĭ们
    -0.22
    Thunk
    -0.22
    è¿ľæĸ¹
    -0.21
    ä¿ĿåŃĺ
    -0.21
    POSITIVE LOGITS
    å®ŀæĸ½ç»ĨåĪĻ
    0.23
    æĪİ
    0.23
    æĢ»èµĦ产
    0.23
     заÑĢегиÑģÑĤÑĢи
    0.23
    大å®Ĺ
    0.22
    .DOM
    0.22
    注åĨĮ
    0.22
    é«Ń
    0.21
     Greenville
    0.21
     Updated
    0.21
    Activations Density 0.035%

    No Known Activations