© 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. 783
    Prev
    Next
    INDEX
    Explanations

    -id, -nd, -rd, -ad suffixes

    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
    ä¸Ģå®ļçļĦ
    -0.25
    dbe
    -0.21
    -minded
    -0.20
    dex
    -0.20
    pler
    -0.20
    един
    -0.20
    plies
    -0.19
    ander
    -0.18
    аÑħ
    -0.18
     ÑħоÑĤÑı
    -0.18
    POSITIVE LOGITS
    irect
    0.34
    olph
    0.34
    esign
    0.33
    imensional
    0.33
    irectional
    0.33
    entifier
    0.33
    isplay
    0.33
    ãĤ¥
    0.32
    imension
    0.31
    istribution
    0.31
    Activations Density 1.652%

    No Known Activations