© 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. 2175
    Prev
    Next
    INDEX
    Explanations

    legal department or function

    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
     lex
    -0.27
     cor
    -0.24
    æī«ä¸Ģæī«
    -0.23
    orative
    -0.22
     Commentary
    -0.21
     dim
    -0.21
    å·¥ä½ľæĬ¥åijĬ
    -0.21
    æĶĢåįĩ
    -0.21
    .rev
    -0.21
     Lex
    -0.21
    POSITIVE LOGITS
    å¤ĸéĥ¨
    0.35
    åĨħéĥ¨
    0.34
    åħ§éĥ¨
    0.33
     external
    0.31
    å¤ĸçķĮ
    0.29
     internal
    0.28
    internal
    0.27
    [group
    0.27
     externally
    0.26
    对åħ¬åı¸
    0.26
    Activations Density 0.934%

    No Known Activations