© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2208
    Prev
    Next
    INDEX
    Explanations

    line numbers and list items

    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
    lâ
    -0.25
    tributes
    -0.23
    ög
    -0.23
    Directed
    -0.23
    çļĦæĢģ度
    -0.22
    ONA
    -0.22
    tribute
    -0.22
     propagation
    -0.22
     IQ
    -0.21
    elles
    -0.21
    POSITIVE LOGITS
    轨
    0.24
     ech
    0.23
    ouch
    0.22
    ç¢Ľ
    0.22
     Suc
    0.21
    å¤ĩçĶ¨
    0.21
     Killed
    0.21
    ABCDE
    0.20
     Illustrated
    0.20
    UnderTest
    0.20
    Activations Density 0.193%

    No Known Activations