© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3424
    Prev
    Next
    INDEX
    Explanations

    graphics, textures, animation, terrain, shadow

    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
    Negative Logits
    urname
    -0.27
     Wage
    -0.27
    Certificate
    -0.26
     indis
    -0.26
    iec
    -0.25
    kees
    -0.25
     dated
    -0.25
    /documents
    -0.25
     diligence
    -0.24
     nationally
    -0.24
    POSITIVE LOGITS
     animations
    0.42
     dynamically
    0.42
    çī¹æķĪ
    0.41
     textures
    0.40
     effects
    0.40
     dynamic
    0.39
    纹çIJĨ
    0.38
    ç²ĴåŃIJ
    0.37
    åĬ¨çĶ»
    0.37
     texture
    0.36
    Activations Density 0.079%

    No Known Activations