© 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. 2115
    Prev
    Next
    INDEX
    Explanations

    cost-benefit ratio, ROI, investment, effectiveness

    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
    arra
    -0.25
    cape
    -0.23
    Stuff
    -0.22
    ArrayOf
    -0.22
    ä»ĸèĩªå·±
    -0.21
    为主
    -0.21
    ä¸ľè¥¿
    -0.21
    plit
    -0.20
    Workers
    -0.20
    缺å°ij
    -0.20
    POSITIVE LOGITS
    æķĪçĽĬ
    0.42
    æĶ¶çĽĬ
    0.29
     expectancy
    0.28
    (effect
    0.28
    ratio
    0.27
     investment
    0.26
    ç»ıæµİæķĪçĽĬ
    0.25
    社ä¼ļæķĪçĽĬ
    0.25
    æķĪåºĶ
    0.25
     ratio
    0.25
    Activations Density 0.009%

    No Known Activations