© 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. 338
    Prev
    Next
    INDEX
    Explanations

    volumes and publication identifiers

    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
     trainers
    -0.25
    orsi
    -0.24
    ForObject
    -0.24
    ToObject
    -0.23
    ánd
    -0.23
    å¿ĥå¾Ĺä½ĵä¼ļ
    -0.23
    trinsic
    -0.22
     setObject
    -0.22
     ÑįкÑģпеÑĢÑĤ
    -0.22
    .Profile
    -0.22
    POSITIVE LOGITS
     newspaper
    0.32
     archive
    0.27
    éĺħè§Ī
    0.26
     archives
    0.26
     newspapers
    0.26
    åı²æĸĻ
    0.25
     Archive
    0.25
    æĬ¥çº¸
    0.25
    æ¯ıåij¨
    0.24
     advertiser
    0.24
    Activations Density 0.018%

    No Known Activations