© 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. 40464
    Prev
    Next
    INDEX
    Explanations

    opening sentences with "We"

    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
    okus
    -0.07
    åĽŀèĢģ家
    -0.07
     responseType
    -0.07
    brains
    -0.07
     uncon
    -0.07
    ially
    -0.06
    UD
    -0.06
    üng
    -0.06
    ud
    -0.06
    Ø°
    -0.06
    POSITIVE LOGITS
    äºĶèĬ±
    0.08
    å°½åħ¶
    0.07
    æ³ķç½ij
    0.07
    ookies
    0.07
    engel
    0.07
    yll
    0.07
    å½°
    0.07
    AGEM
    0.06
     sinh
    0.06
    缴è¾ĸ
    0.06
    Activations Density 0.042%

    No Known Activations