© 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. 33630
    Prev
    Next
    INDEX
    Explanations

    numbers and enumeration

    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
    {text
    -0.09
    ebr
    -0.08
    วัà¸Ĵà¸Ļ
    -0.08
    TextLabel
    -0.08
    opus
    -0.08
    ofday
    -0.08
    缸åħ³æĿIJæĸĻ
    -0.08
     eskort
    -0.07
    åħļå§Ķåī¯ä¹¦è®°
    -0.07
     uite
    -0.07
    POSITIVE LOGITS
     rewritten
    0.08
     equation
    0.07
    :
    0.07
    Rew
    0.06
    aw
    0.06
    ï¼ļ“
    0.06
    idar
    0.06
    æ³ķ令
    0.06
    è¦ģæ±ĤçļĦ
    0.06
     reproduced
    0.06
    Activations Density 0.001%

    No Known Activations