© 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. 1068
    Prev
    Next
    INDEX
    Explanations

    coarse microstructure, sparse signals

    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
    ris
    -0.23
    $$$$
    -0.21
    请æķĻ
    -0.20
    åħī彩
    -0.20
     Tac
    -0.20
     incorpor
    -0.19
    常æĢģåĮĸ
    -0.19
    atically
    -0.19
     unic
    -0.19
    èĩªè§ī
    -0.19
    POSITIVE LOGITS
    人éĢī
    0.25
    ening
    0.25
     miser
    0.24
     rÃłng
    0.23
    -haired
    0.23
     جدا
    0.23
     enough
    0.23
    mland
    0.22
    /fast
    0.21
    TextLabel
    0.21
    Activations Density 0.004%

    No Known Activations