© 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. 29282
    Prev
    Next
    INDEX
    Explanations

    numbers followed by weights or units

    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
    ÏĥÏĦο
    -0.08
    BUFF
    -0.07
    ROY
    -0.07
    atter
    -0.07
    κε
    -0.07
    .fm
    -0.07
    è¯Ģ
    -0.07
    reste
    -0.07
    ager
    -0.07
    æĬ¥ç¤¾
    -0.07
    POSITIVE LOGITS
    ernal
    0.07
    åij¨æľŁçļĦ
    0.07
    èݱ德
    0.06
    isoft
    0.06
    é¦ĭ
    0.06
    槽
    0.06
    è½®åĽŀ
    0.06
    éĹ´éļĶ
    0.06
     Vel
    0.06
     Cin
    0.06
    Activations Density 0.267%

    No Known Activations