© 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. 15826
    Prev
    Next
    INDEX
    Explanations

    methodology and approach

    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
    idor
    -0.08
    agraph
    -0.08
    cies
    -0.08
    妮
    -0.07
     dauerhaft
    -0.07
    estina
    -0.07
    åħ¨å¤©
    -0.07
    ationship
    -0.07
    åij¼åĴĮ
    -0.07
    çłĶ究æĺ¾ç¤º
    -0.07
    POSITIVE LOGITS
     principles
    0.10
     methodology
    0.08
     techniques
    0.08
     framework
    0.08
    ink
    0.08
    æ¡Ĩæŀ¶
    0.08
     successive
    0.08
     technique
    0.08
     principle
    0.08
     sequential
    0.07
    Activations Density 0.043%

    No Known Activations