© 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. 1572
    Prev
    Next
    INDEX
    Explanations

    other things

    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
    æľ¬èº«çļĦ
    -0.23
    orf
    -0.22
    /resource
    -0.21
     Todd
    -0.21
    bw
    -0.20
    æ©¡
    -0.20
     widest
    -0.20
    ç®ĢåİĨ
    -0.20
     Pictures
    -0.20
     staggering
    -0.20
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.34
     other
    0.31
    åĪ«çļĦ
    0.31
    åĽłç´ł
    0.30
     factors
    0.30
    åħ¶ä»ĸçļĦ
    0.29
     aspects
    0.29
    çļĦåĽłç´ł
    0.27
    (other
    0.27
    æĸ¹éĿ¢
    0.26
    Activations Density 0.058%

    No Known Activations