© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 360
    Prev
    Next
    INDEX
    Explanations

    lists composed of other lists

    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
     conjug
    -0.24
     portion
    -0.22
    æĺ¾
    -0.22
    伦
    -0.22
    并åIJij
    -0.22
     buoy
    -0.22
    åħ·
    -0.21
    éĶº
    -0.21
    èĩ´
    -0.20
    姣
    -0.20
    POSITIVE LOGITS
    çļĦçIJĨ念
    0.25
    openid
    0.24
    ABCDEFG
    0.24
    ,event
    0.23
     pragma
    0.22
    abouts
    0.21
    agua
    0.21
     reform
    0.21
    çĻ½éĵ¶
    0.20
    agem
    0.20
    Activations Density 0.085%

    No Known Activations