© 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. 495
    Prev
    Next
    INDEX
    Explanations

    rental property

    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
    ä¸ĵ人
    -0.26
    æĪij们认为
    -0.24
    æķ°éĩı
    -0.22
     whole
    -0.22
    头èĦij
    -0.21
    åĬŀ好
    -0.21
    è®¤çľŁåŃ¦ä¹ł
    -0.21
    whole
    -0.21
    plural
    -0.21
    weets
    -0.20
    POSITIVE LOGITS
    翳
    0.24
    iful
    0.23
    -energy
    0.22
    æĬµ
    0.21
     neutrality
    0.21
    潦
    0.21
    ers
    0.21
    çļĦèĥ½éĩı
    0.21
     repro
    0.20
    ennie
    0.20
    Activations Density 0.003%

    No Known Activations