© 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. 3116
    Prev
    Next
    INDEX
    Explanations

    become followed by a state or attribute

    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
    ä½Ĩä¹Ł
    -0.24
     Starter
    -0.22
     rethink
    -0.22
    mans
    -0.21
    nego
    -0.21
     hãy
    -0.20
     Jelly
    -0.19
    /small
    -0.19
     behalf
    -0.19
    -esque
    -0.19
    POSITIVE LOGITS
    aks
    0.28
     evident
    0.22
    ëłģ
    0.22
    ä¸Ģå®ļçļĦ
    0.21
     trivial
    0.21
     accustomed
    0.21
     too
    0.21
    iley
    0.21
    éĺĹ
    0.21
     difficult
    0.21
    Activations Density 0.053%

    No Known Activations