© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38843
    Prev
    Next
    INDEX
    Explanations

    applications and admissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rances
    -0.08
    ɵ
    -0.08
    hoot
    -0.08
    åħįåĨł
    -0.08
    amientos
    -0.08
    鼷æĸ¯
    -0.08
    çĶ±è¢«åijĬ
    -0.08
    è©«
    -0.07
    éĢļè¿ĩçĶµè¯Ŀ
    -0.07
    æľ¬äº§åĵģ
    -0.07
    POSITIVE LOGITS
     applications
    0.11
     Applications
    0.10
    åºĶçĶ¨åľºæĻ¯
    0.09
    Applications
    0.09
    applications
    0.08
    åºĶçĶ¨ä¸Ń
    0.08
    åºĶçĶ¨
    0.08
    ä¸ŃçļĦåºĶçĶ¨
    0.08
    ahl
    0.07
     implications
    0.07
    Activations Density 0.205%

    No Known Activations