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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2266
    Prev
    Next
    INDEX
    Explanations

    biblical names and proper nouns

    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
    oller
    -0.24
    ArrayType
    -0.23
     coaster
    -0.23
    èIJ§
    -0.22
    åħ¬ä¼Ĺ
    -0.22
     Claw
    -0.22
    åįĩ温
    -0.22
     hugs
    -0.22
    é£Ļ
    -0.22
     Goals
    -0.21
    POSITIVE LOGITS
    -era
    0.29
     Eve
    0.28
    Traversal
    0.28
    alem
    0.27
     myth
    0.27
     caret
    0.25
     myths
    0.25
    éģĹ
    0.25
    çĶŁèĤ²
    0.25
    _hid
    0.24
    Activations Density 0.008%

    No Known Activations