© 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. 888
    Prev
    Next
    INDEX
    Explanations

    intelligent design

    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
     Massive
    -0.23
    imat
    -0.22
    masters
    -0.21
    羣æŃ£çļĦ
    -0.21
    MAS
    -0.21
    è¿ĺä¸įæĺ¯
    -0.21
    åĪĽéĢłåĬĽ
    -0.21
    centers
    -0.21
    forme
    -0.20
    ILING
    -0.20
    POSITIVE LOGITS
     enough
    0.26
    .attach
    0.23
     sof
    0.22
     literature
    0.22
     pul
    0.22
     boy
    0.22
    æĻ°
    0.22
     literary
    0.21
     rhet
    0.21
    uxtap
    0.21
    Activations Density 0.005%

    No Known Activations