© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    time and channel numbers

    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
    nev
    -0.24
    èĥ¥
    -0.23
    stock
    -0.23
    staff
    -0.22
    stage
    -0.22
    енÑĮ
    -0.21
    ikes
    -0.21
     commissions
    -0.21
    tech
    -0.21
    tle
    -0.21
    POSITIVE LOGITS
     ores
    0.24
     Alloc
    0.22
    æĬ«éľ²
    0.22
    çĭ¸
    0.22
    DED
    0.22
     ecological
    0.21
    migration
    0.21
    ProgressDialog
    0.21
    çķ´
    0.21
    ozy
    0.21
    Activations Density 0.062%

    No Known Activations