© 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. 1823
    Prev
    Next
    INDEX
    Explanations

    RESTful API

    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
    .expect
    -0.23
    ombo
    -0.22
    [][
    -0.22
     Trilogy
    -0.21
    TypeEnum
    -0.21
    大楼
    -0.21
    Scheduled
    -0.21
    éĥ½è¯´
    -0.21
    rente
    -0.21
    .inst
    -0.21
    POSITIVE LOGITS
     tiled
    0.23
    ÃŃch
    0.21
    ustin
    0.21
    .stamp
    0.21
    ALLY
    0.21
    ferred
    0.20
    è±ķ
    0.20
    人æĸĩ
    0.20
    好åIJ§
    0.20
    href
    0.20
    Activations Density 0.004%

    No Known Activations