© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 12681
    Prev
    Next
    INDEX
    Explanations

    phrases connecting words

    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
    æ¹Ľ
    -0.06
    ##_
    -0.06
    table
    -0.06
     dat
    -0.06
    cio
    -0.06
    å¾·éŁ³
    -0.06
     designation
    -0.06
    erti
    -0.06
    cea
    -0.06
    ãĥĻãĥ«
    -0.05
    POSITIVE LOGITS
     {}:
    0.08
    }):
    0.08
    )):
    0.08
    inois
    0.08
    ofilm
    0.07
    rane
    0.07
    æī«çłģåħ³æ³¨
    0.07
    ÑĢам
    0.07
    æľºçİĩ
    0.07
    ailles
    0.07
    Activations Density 0.009%

    No Known Activations