© 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. 25250
    Prev
    Next
    INDEX
    Explanations

    reliable discrimination

    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
    为äºĨ满足
    -0.11
    为满足
    -0.09
    cesi
    -0.08
    并åħ¥
    -0.08
     ÐIJналоги
    -0.08
    iales
    -0.08
    icked
    -0.07
    вне
    -0.07
    istrib
    -0.07
     everywhere
    -0.07
    POSITIVE LOGITS
    åı¯éĿłçļĦ
    0.10
     reliable
    0.10
     detection
    0.10
    è¿Ļç§įæĸ¹æ³ķ
    0.10
     detecting
    0.09
     unreliable
    0.09
     Reliable
    0.09
     discrimination
    0.09
    è¿Ļ个æĸ¹æ³ķ
    0.09
     reliably
    0.09
    Activations Density 0.149%

    No Known Activations