© 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. 1212
    Prev
    Next
    INDEX
    Explanations

    copyright, reserved rights

    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
     lá»Ļ
    -0.24
    çģŃ
    -0.24
     downgrade
    -0.24
    .setInput
    -0.23
    ä»Ĺ
    -0.23
    æľīåĪ©äºİ
    -0.22
    enable
    -0.22
    ÐĿÐIJ
    -0.22
    approve
    -0.21
     sup
    -0.21
    POSITIVE LOGITS
    åİŁåĪĽ
    0.53
     copyrighted
    0.35
    çĭ¬ä¸ĢæĹłäºĮ
    0.33
    çīĪæĿĥæīĢæľī
    0.32
     copyright
    0.32
    çĭ¬çī¹
    0.31
     copyrights
    0.31
     patented
    0.30
    ãĤªãĥªãĤ¸ãĥĬãĥ«
    0.30
     ©
    0.30
    Activations Density 0.035%

    No Known Activations