© 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. 752
    Prev
    Next
    INDEX
    Explanations

    corporate activities and entities

    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
    small
    -0.23
    sort
    -0.21
    slow
    -0.21
    nya
    -0.21
    ungen
    -0.21
    éĵİ
    -0.21
    erman
    -0.20
    åĴĮæĶ¯æĮģ
    -0.20
    ãģ¹ãģį
    -0.20
    si
    -0.20
    POSITIVE LOGITS
    /business
    0.27
    åĮĸçļĦ
    0.27
    -minded
    0.26
    -level
    0.26
     minded
    0.24
     дÑĥÑħ
    0.23
    -sponsored
    0.23
    /com
    0.23
    å±ĤéĿ¢
    0.22
    çĶŁæ¶¯
    0.21
    Activations Density 0.012%

    No Known Activations