© 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. 3472
    Prev
    Next
    INDEX
    Explanations

    observed data and phenomena

    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
    éĥ½æľīåı¯èĥ½
    -0.09
    lix
    -0.09
    abase
    -0.08
    ãĤ¤ãĥĻ
    -0.08
     liable
    -0.08
     Edels
    -0.08
    amana
    -0.08
    jem
    -0.07
    overe
    -0.07
    ifu
    -0.07
    POSITIVE LOGITS
    çݰ象
    0.09
    çŃīçݰ象
    0.09
    çļĦçݰ象
    0.09
     phenomen
    0.09
     phenomena
    0.08
     behavior
    0.08
     puzz
    0.08
     Puzz
    0.08
     behaviour
    0.07
     inexp
    0.07
    Activations Density 0.042%

    No Known Activations