© 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. 2670
    Prev
    Next
    INDEX
    Explanations

    layer or layers

    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
    éĻIJæŶ
    -0.26
     teleport
    -0.26
     Markup
    -0.25
     welcome
    -0.23
     offline
    -0.23
    Dump
    -0.23
    俳
    -0.23
     revise
    -0.23
     robots
    -0.23
     Waiting
    -0.23
    POSITIVE LOGITS
    å±Ĥ
    0.47
     layers
    0.43
    _layers
    0.42
    ä¸Ģå±Ĥ
    0.41
    層
    0.40
     layer
    0.40
    layers
    0.37
    .layers
    0.36
    èĬ¯
    0.36
     Layers
    0.36
    Activations Density 0.205%

    No Known Activations