© 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. 3026
    Prev
    Next
    INDEX
    Explanations

    counted, counts, counting

    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
     Pron
    -0.26
     aur
    -0.24
    /request
    -0.23
     Something
    -0.23
     requested
    -0.22
    legg
    -0.22
    _requested
    -0.22
    maybe
    -0.22
     suck
    -0.21
    gram
    -0.21
    POSITIVE LOGITS
     counted
    0.52
     counts
    0.47
    计åħ¥
    0.45
     counting
    0.43
    æī£éĻ¤
    0.43
     Counts
    0.42
     contribution
    0.40
    counts
    0.38
    è´¡çĮ®
    0.36
     contributions
    0.36
    Activations Density 0.089%

    No Known Activations