© 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. 49670
    Prev
    Next
    INDEX
    Explanations

    branch connections

    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
    -fashioned
    -0.11
    缸è¾ħ缸æĪIJ
    -0.09
    ehme
    -0.09
    anders
    -0.08
    berto
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    ander
    -0.08
    teen
    -0.08
    миÑĢ
    -0.08
    bert
    -0.08
    POSITIVE LOGITS
    er
    0.10
    ÙĬÙĨ
    0.09
    less
    0.09
    yard
    0.08
    ry
    0.08
    ноÑģÑĤей
    0.07
    odox
    0.07
    bons
    0.07
    uela
    0.07
    korb
    0.07
    Activations Density 0.032%

    No Known Activations