© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44209
    Prev
    Next
    INDEX
    Explanations

    limits of integration

    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
    å»¶æľŁ
    -0.07
    UMA
    -0.07
    anky
    -0.07
    ENTOS
    -0.07
    ФÐIJ
    -0.06
    |string
    -0.06
     dán
    -0.06
    unjuk
    -0.06
    åı¸æ³ķåįıåĬ©
    -0.06
    Ä«j
    -0.06
    POSITIVE LOGITS
    为ä¿Ŀè¯ģ
    0.10
    以ä¿Ŀè¯ģ
    0.10
    æľĢèµ·çłģ
    0.09
    æīįèĥ½ä¿Ŀè¯ģ
    0.09
    ä¿Ŀè¯ģåħ¶
    0.09
     limits
    0.09
    æīįèĥ½æľī
    0.08
    èĩ³å°ijè¦ģ
    0.08
    ä¸įèĥ½è¶ħè¿ĩ
    0.08
    为äºĨä¿Ŀè¯ģ
    0.08
    Activations Density 0.003%

    No Known Activations