© 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
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 146
    Prev
    Next
    INDEX
    Explanations

    directors and writers

    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
    ä¹ĭ家
    -0.23
    ulan
    -0.23
    æ´»åĭķ
    -0.23
    çĵł
    -0.22
     beaten
    -0.22
    umni
    -0.22
    -rad
    -0.22
    Occ
    -0.22
    åķĨæĬ¥
    -0.21
    æ´»åĬ¨
    -0.21
    POSITIVE LOGITS
    éĿ¢éĥ¨
    0.24
    odie
    0.23
     cpt
    0.23
     Bret
    0.22
    inst
    0.21
     noc
    0.21
    以å¾Ģ
    0.21
    adows
    0.21
    çĽij
    0.21
    代
    0.21
    Activations Density 0.023%

    No Known Activations