© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 35
    Prev
    Next
    INDEX
    Explanations

    . or memberOf

    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
    è¿Ļ个åIJįåŃĹ
    -0.26
    ATYPE
    -0.25
    _svc
    -0.23
    .NAME
    -0.22
    设æĸ½å»ºè®¾
    -0.22
    classname
    -0.22
    ç³ģ
    -0.21
    Ế
    -0.21
    STDOUT
    -0.21
    routing
    -0.21
    POSITIVE LOGITS
     begs
    0.26
    纪
    0.24
    olean
    0.23
    á»Ĺ
    0.23
    è°ĵ
    0.23
     Org
    0.22
     (?)
    0.22
     cort
    0.22
     unlucky
    0.22
     Exploration
    0.21
    Activations Density 0.002%

    No Known Activations