© 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. 3158
    Prev
    Next
    INDEX
    Explanations

    Americas

    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
    Negative Logits
    eing
    -0.23
    åī¡
    -0.23
     Meaning
    -0.23
     Kou
    -0.22
    urat
    -0.22
    avenport
    -0.22
    uates
    -0.22
    arde
    -0.22
     pil
    -0.22
     Iraqi
    -0.22
    POSITIVE LOGITS
     Colomb
    0.30
    ç¾İæ´²
    0.30
    Brazil
    0.28
     Hemisphere
    0.25
    Canadian
    0.25
    åĬłæĭ¿
    0.25
     saturn
    0.24
     Brazilian
    0.24
    çĥŃ带
    0.24
     Braz
    0.24
    Activations Density 0.021%

    No Known Activations