© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 253
    Prev
    Next
    INDEX
    Explanations

    support stand

    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
    çݺ
    -0.24
    LocalizedString
    -0.22
    guard
    -0.22
    âĮ«
    -0.22
    dens
    -0.22
    转移
    -0.22
    -transfer
    -0.21
    .replace
    -0.21
    ç¤ģ
    -0.21
    car
    -0.21
    POSITIVE LOGITS
    è§Ĵ度
    0.29
     upright
    0.28
    Angle
    0.28
    angle
    0.28
     angle
    0.27
     angled
    0.26
    angles
    0.26
    åĴĮå¹³
    0.25
     Kindle
    0.25
    çļĦè§Ĵ度
    0.25
    Activations Density 0.023%

    No Known Activations