© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    verifying identity and authenticity

    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
    efa
    -0.24
    åŃIJå¼Ł
    -0.24
    notation
    -0.24
    åłķ
    -0.23
    Mind
    -0.23
    æĪŁ
    -0.23
     notation
    -0.23
    pread
    -0.23
    -fin
    -0.23
    Scient
    -0.22
    POSITIVE LOGITS
     bona
    0.28
    éªĮè¯ģ
    0.25
    validator
    0.24
     Hills
    0.24
    enticator
    0.24
     Cyr
    0.23
     bracelet
    0.23
     welcomed
    0.23
    å¦ĤæĦı
    0.23
    wend
    0.22
    Activations Density 0.014%

    No Known Activations