© 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. 41106
    Prev
    Next
    INDEX
    Explanations

    rental and property usage

    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
    éĤ£åı¯
    -0.07
     formul
    -0.07
     Banks
    -0.07
     arresting
    -0.07
    å°Ķåħĭ
    -0.07
     universally
    -0.06
    inkin
    -0.06
    æĥĬéŃĤ
    -0.06
    trained
    -0.06
     phosph
    -0.06
    POSITIVE LOGITS
    使çĶ¨è¯¥
    0.11
    å°Ĩ该
    0.09
    对该
    0.09
    æĸ¹å¼ı使çĶ¨
    0.08
    使çĶ¨åIJİ
    0.08
    è½¬ç§Ł
    0.08
    æī¿ç§Ł
    0.08
    Ñħи
    0.08
    çļĦ使çĶ¨
    0.08
     usage
    0.08
    Activations Density 0.094%

    No Known Activations