© 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. 1009
    Prev
    Next
    INDEX
    Explanations

    mine alone, own reflections

    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
    人æµģ
    -0.23
    leta
    -0.23
    éĻIJé¢Ŀ
    -0.23
    æľīåIJįçļĦ
    -0.22
     priority
    -0.22
    leh
    -0.22
     URLRequest
    -0.21
    urma
    -0.21
    UserData
    -0.21
    LoginForm
    -0.21
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.28
    个æĢ§
    0.27
    ä»ħ代表
    0.25
    æľªç»ı
    0.23
     Penny
    0.23
    agger
    0.23
     convictions
    0.23
    个æĢ§åĮĸ
    0.23
    个人è§ĤçĤ¹
    0.22
     Shake
    0.22
    Activations Density 0.005%

    No Known Activations