© 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. 2068
    Prev
    Next
    INDEX
    Explanations

    memory and storage units (MB, GB, K, M)

    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
     NOM
    -0.23
     schedule
    -0.22
    èģĺçĶ¨
    -0.22
     hangs
    -0.21
     dresses
    -0.21
     unsus
    -0.21
    æĸ°éĽ¶åĶ®
    -0.21
    exter
    -0.20
    å±ĭ
    -0.20
     unreal
    -0.20
    POSITIVE LOGITS
    pair
    0.25
    bands
    0.25
    mv
    0.24
    MV
    0.24
    x
    0.24
    éģį
    0.24
    èķĻ
    0.24
    aries
    0.23
    ptr
    0.23
    mond
    0.23
    Activations Density 0.012%

    No Known Activations