© 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. 24164
    Prev
    Next
    INDEX
    Explanations

    paper abstract

    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
    对è¿ĻäºĽ
    -0.08
    èĢĮè¿ĻäºĽ
    -0.08
    å¤ļä¸ĢäºĽ
    -0.08
    árt
    -0.08
    ä¸į妨
    -0.08
    arli
    -0.07
    ackt
    -0.07
    empi
    -0.07
    oday
    -0.07
    >window
    -0.07
    POSITIVE LOGITS
    itin
    0.07
    zil
    0.07
     Rosenberg
    0.07
    ç¥ī
    0.06
    Tel
    0.06
    ciel
    0.06
    åıĬè¦ģæ±Ĥ
    0.06
     Perr
    0.06
     rev
    0.06
    æľ¬é¢ĺèĢĥæŁ¥
    0.06
    Activations Density 0.007%

    No Known Activations