© 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. 60281
    Prev
    Next
    INDEX
    Explanations

    JSON keys and values

    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
    oland
    -0.07
    ("").
    -0.07
    +
    -0.07
     Vance
    -0.07
    өг
    -0.06
    +.
    -0.06
     plus
    -0.06
    æ©
    -0.06
    ayo
    -0.06
    uye
    -0.06
    POSITIVE LOGITS
    ":
    0.08
    !:
    0.08
    ieces
    0.08
    !!:
    0.07
    _:
    0.07
    "":
    0.07
    )did
    0.07
    \":
    0.07
    ”:
    0.07
    æīĢå±ŀåĪĨç±»
    0.07
    Activations Density 0.300%

    No Known Activations