© 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. 2351
    Prev
    Next
    INDEX
    Explanations

    list items initiated by punctuation

    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
    åIJİåĨį
    -0.24
    åĽĽæĺ¯
    -0.24
     PERFORMANCE
    -0.24
    åĢ¼å¾Ĺä¸Ģ
    -0.23
     FEATURES
    -0.23
     ATTRIBUTE
    -0.23
    éłħ
    -0.23
    -note
    -0.23
     REPLACE
    -0.23
    (CONT
    -0.22
    POSITIVE LOGITS
     %↵↵
    0.28
    %↵↵
    0.27
    åIJĦç±»
    0.27
    à¤Ī
    0.26
    oriously
    0.25
    +↵↵
    0.25
    oug
    0.25
     high
    0.23
     %↵
    0.23
    æĹł
    0.23
    Activations Density 0.126%

    No Known Activations