© 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. 654
    Prev
    Next
    INDEX
    Explanations

    located in

    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
    ä½Ĩä¹Ł
    -0.23
    说èĩªå·±
    -0.22
     theirs
    -0.22
     someday
    -0.21
     politic
    -0.21
    说çļĦè¯Ŀ
    -0.21
    åı¯æĥ³
    -0.21
     explanation
    -0.21
    woke
    -0.21
    /pol
    -0.20
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.28
    ä¸Ģå®ļçļĦ
    0.25
    æŃ£åĢ¼
    0.25
    以ä¸ĭåĩłä¸ª
    0.24
    ä¸Ĭæĸ¹
    0.24
    çļĦæĺ¯
    0.23
     <![
    0.23
    çī¹æ®ĬçļĦ
    0.22
    çĶ±
    0.22
    :
    0.22
    Activations Density 0.155%

    No Known Activations