© 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. 1824
    Prev
    Next
    INDEX
    Explanations

    SSD Controllers Cloud Storage

    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
    éļĻ
    -0.23
    /GPL
    -0.23
    .hm
    -0.23
    éĤ¯
    -0.23
    icator
    -0.23
    holm
    -0.23
    Broker
    -0.22
    ær
    -0.22
     Mills
    -0.22
    hoff
    -0.22
    POSITIVE LOGITS
    æ¡ĮéĿ¢
    0.30
    ctrl
    0.27
    æĶ¯æĮģåĬĽåº¦
    0.26
    æŀķ头
    0.25
    æĮ¥
    0.25
    ç¼µ
    0.24
     closet
    0.24
     Vault
    0.23
    æ¡Į
    0.23
    éĵł
    0.23
    Activations Density 0.009%

    No Known Activations