© 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. 30867
    Prev
    Next
    INDEX
    Explanations

    absolute value or basis

    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
    LOPT
    -0.08
    笳
    -0.08
    åħ³éĶ®è¯į
    -0.08
    åĢ¾åĬĽ
    -0.08
    代ä¼ļ
    -0.08
    ")(
    -0.07
    BW
    -0.07
    为代表çļĦ
    -0.07
    ä¸ļåįıä¼ļ
    -0.07
    _OPTS
    -0.07
    POSITIVE LOGITS
     absol
    0.10
    OLUTE
    0.08
    ç»Ŀ对
    0.08
     absolute
    0.07
    ordo
    0.07
    versch
    0.07
    Absolute
    0.07
    vers
    0.07
    çĸµ
    0.07
     raw
    0.07
    Activations Density 0.013%

    No Known Activations