© 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. 25222
    Prev
    Next
    INDEX
    Explanations

    directional orientation

    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
     cheva
    -0.08
    .handleError
    -0.08
    oram
    -0.08
    bloc
    -0.08
    è¿ĻäºĽå°ı
    -0.08
    åĸľéĹ»ä¹IJ
    -0.08
    Õ¥Õ½
    -0.07
    landa
    -0.07
    BUFFER
    -0.07
    getResult
    -0.07
    POSITIVE LOGITS
     singled
    0.09
    åıĤèĢĥ
    0.09
     reference
    0.09
    éĶļ
    0.08
     defining
    0.08
     distinguished
    0.08
    åıĤçħ§
    0.08
     direction
    0.08
    reference
    0.08
     Reference
    0.08
    Activations Density 0.014%

    No Known Activations