© 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. 2071
    Prev
    Next
    INDEX
    Explanations

    Vanderbilt, Highland

    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
    iore
    -0.23
    fire
    -0.23
    y
    -0.22
    s
    -0.21
    rzy
    -0.21
    a
    -0.21
    scape
    -0.21
    i
    -0.21
    ä¸Ńåħ³
    -0.21
    iÄĩ
    -0.21
    POSITIVE LOGITS
    大åѦ
    0.22
     feud
    0.20
     university
    0.19
    èĥº
    0.19
     chute
    0.18
    åºĦåĽŃ
    0.18
    à¹ī
    0.18
     дÑĥÑħ
    0.17
     amour
    0.17
    emon
    0.17
    Activations Density 0.004%

    No Known Activations