© 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. 981
    Prev
    Next
    INDEX
    Explanations

    LLVM Compiler, Google Inc

    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
    reate
    -0.25
    ocumented
    -0.23
    çīĪ
    -0.22
     Angry
    -0.22
    WithContext
    -0.21
    转åĮĸ为
    -0.21
     Lightweight
    -0.21
    éĢģè¾¾
    -0.21
    laps
    -0.20
    ocracy
    -0.20
    POSITIVE LOGITS
     downtime
    0.24
     Recru
    0.22
    /sbin
    0.21
     sims
    0.21
     deltaTime
    0.21
     mom
    0.21
    )**
    0.21
    allocator
    0.21
     reco
    0.20
     Mom
    0.20
    Activations Density 0.006%

    No Known Activations