© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1245
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and questions

    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
    æªĢ
    -0.26
    ä¼Ĭå§ĭ
    -0.24
    æĿ¥æºIJ
    -0.23
    é«ĺå°Ķ
    -0.23
    “At
    -0.22
    “Yes
    -0.22
     ethn
    -0.22
    çĻ½é©¬
    -0.21
    ExecutionContext
    -0.21
    åħ¸
    -0.21
    POSITIVE LOGITS
    ocop
    0.23
    iere
    0.23
    ä»ĸ们éĥ½
    0.22
     sieve
    0.22
    iesel
    0.22
    åıĪ好åıĪ
    0.22
    ouple
    0.22
    Ionic
    0.21
    orical
    0.21
    hiba
    0.21
    Activations Density 0.003%

    No Known Activations