© 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. 24786
    Prev
    Next
    INDEX
    Explanations

    point recovery

    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
    èĽ®
    -0.07
    åħĪåľ¨
    -0.07
    czÄħ
    -0.07
    kens
    -0.07
    pd
    -0.06
    鼷
    -0.06
    æIJŀ
    -0.06
    ROL
    -0.06
    èł»
    -0.06
    ice
    -0.06
    POSITIVE LOGITS
    among
    0.09
    levant
    0.08
     ÑģÑĢеди
    0.08
     among
    0.07
     orto
    0.07
    rim
    0.07
     Borr
    0.07
     later
    0.07
    ENAME
    0.07
    ruk
    0.07
    Activations Density 0.516%

    No Known Activations