© 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. 758
    Prev
    Next
    INDEX
    Explanations

    custom component or module

    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
    ThreadId
    -0.26
    åĨħéĻĨ
    -0.23
    ience
    -0.23
     infuri
    -0.22
    incy
    -0.22
    iesel
    -0.22
     currentDate
    -0.21
    çĮĽçĥĪ
    -0.21
    akh
    -0.21
    è¿Ļ份
    -0.21
    POSITIVE LOGITS
     custom
    0.64
    å®ļåĪ¶
    0.54
     Custom
    0.53
    custom
    0.52
    .custom
    0.50
    -custom
    0.49
    (custom
    0.49
    Custom
    0.48
     customized
    0.47
     customization
    0.47
    Activations Density 0.593%

    No Known Activations