© 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. 1813
    Prev
    Next
    INDEX
    Explanations

    custom, customized, customize

    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
    è¿Ļ段
    -0.25
    hydration
    -0.23
    çĿ¡åīį
    -0.22
    credited
    -0.22
    spb
    -0.21
    /light
    -0.21
     automát
    -0.21
    reon
    -0.21
    _receipt
    -0.21
    emale
    -0.20
    POSITIVE LOGITS
    å®ļåĪ¶
    0.56
     custom
    0.47
     customization
    0.46
    /custom
    0.45
     customized
    0.45
    custom
    0.43
     Custom
    0.42
    (custom
    0.41
    Custom
    0.40
     customize
    0.40
    Activations Density 0.139%

    No Known Activations