© 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. 42072
    Prev
    Next
    INDEX
    Explanations

    third

    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
     *
    -0.07
    º
    -0.06
    ward
    -0.06
     f
    -0.06
     Th
    -0.06
    ural
    -0.06
    arg
    -0.06
     '
    -0.06
    led
    -0.06
    -0.06
    POSITIVE LOGITS
    صÙĬ
    0.09
    æīĢå±ŀåĪĨç±»
    0.09
    çľĭçľĭåIJ§
    0.09
    enant
    0.09
    åĪĨ享åĪ°
    0.08
    _SHARED
    0.08
    auta
    0.08
    inom
    0.08
     pse
    0.08
    ׾×ĺ
    0.08
    Activations Density 0.012%

    No Known Activations