© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 346
    Prev
    Next
    INDEX
    Explanations

    closing methods and resources

    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
    anship
    -0.23
    opia
    -0.23
    åİĨåı²æĸ°
    -0.23
    éĶ¤
    -0.23
     Happiness
    -0.23
    urb
    -0.22
    .tab
    -0.22
    éģķãģĦ
    -0.22
     muslim
    -0.22
     med
    -0.21
    POSITIVE LOGITS
    åħ³éĹŃ
    0.37
    /close
    0.35
    éĶĢæ¯ģ
    0.31
    dealloc
    0.31
    .Dispose
    0.30
    æĶ¶åĽŀ
    0.30
     onDestroy
    0.30
     dealloc
    0.29
    _DESTROY
    0.28
     gracefully
    0.28
    Activations Density 0.175%

    No Known Activations