© 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. 1896
    Prev
    Next
    INDEX
    Explanations

    brook names and places

    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
    ãĤ§
    -0.25
    ArrayOf
    -0.21
    ROID
    -0.20
    ëģĶ
    -0.19
     Thousand
    -0.19
    itives
    -0.18
    ités
    -0.18
    ToOne
    -0.18
     пÑĢоÑģмоÑĤÑĢ
    -0.18
     equipments
    -0.18
    POSITIVE LOGITS
    side
    0.33
    dale
    0.24
    sw
    0.23
    shan
    0.23
    sville
    0.23
    manship
    0.22
    sWith
    0.22
    ships
    0.22
    ridge
    0.21
    shire
    0.21
    Activations Density 0.009%

    No Known Activations