© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    multi-family and unstable

    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
    skill
    -0.26
    sentence
    -0.25
    åľ¨çİ°åľº
    -0.23
    å¢Ģ
    -0.23
    egie
    -0.22
     puss
    -0.22
    笨
    -0.22
    zens
    -0.22
    åĨħéĻĨ
    -0.22
     upstairs
    -0.22
    POSITIVE LOGITS
    å¼±
    0.29
     low
    0.26
    ä½İ
    0.24
     Nes
    0.23
    .TabStop
    0.23
     cat
    0.23
     high
    0.22
    ity
    0.22
    /high
    0.22
     cost
    0.22
    Activations Density 0.001%

    No Known Activations