© 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. 1532
    Prev
    Next
    INDEX
    Explanations

    Regional followed by institution or service

    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
    belief
    -0.24
    åħ·ä½ĵåĨħ容
    -0.23
    æĴŃæĬ¥
    -0.22
    éĥ¨åĪĨåľ°åĮº
    -0.22
    èĽĨ
    -0.22
    haul
    -0.21
    åħħå®ŀ
    -0.21
    åľ¨åħ¨çIJĥ
    -0.21
    bounds
    -0.21
     ridicule
    -0.21
    POSITIVE LOGITS
     center
    0.26
     Center
    0.26
     Airport
    0.25
     Hospital
    0.23
     CR
    0.23
     hospital
    0.23
     omn
    0.23
    管
    0.23
     Target
    0.23
     Graph
    0.23
    Activations Density 0.006%

    No Known Activations