© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1282
    Prev
    Next
    INDEX
    Explanations

    apocrine, endocrine, proteins, capacitive

    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
    æĸ¤
    -0.28
    overs
    -0.27
     amb
    -0.27
    /action
    -0.24
     equivalent
    -0.24
    ç«ĭãģ¦
    -0.23
    è¯
    -0.23
    /view
    -0.23
    /stat
    -0.23
    ignite
    -0.23
    POSITIVE LOGITS
    edException
    0.23
    AAF
    0.23
    ooled
    0.23
    жал
    0.22
    æ¼ķ
    0.22
    IGIN
    0.22
    ä¸įèµ·
    0.21
     Treasure
    0.21
     patented
    0.21
    è¢ħ
    0.21
    Activations Density 0.095%

    No Known Activations