© 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. 732
    Prev
    Next
    INDEX
    Explanations

    center of

    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
    纷纷
    -0.22
    robots
    -0.22
    çļĦåľ°ä½į
    -0.21
    å¾Ĺèµ·
    -0.21
    dirs
    -0.21
    (metric
    -0.20
     Domin
    -0.20
    æ½¼
    -0.20
    atten
    -0.20
     Trio
    -0.20
    POSITIVE LOGITS
    OfFile
    0.27
    OfString
    0.25
    ity
    0.24
    ä¸įæĺĵ
    0.23
    icals
    0.23
    põe
    0.22
    ewith
    0.22
    URLRequest
    0.21
    KeySpec
    0.21
    iator
    0.21
    Activations Density 0.011%

    No Known Activations