© 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. 64993
    Prev
    Next
    INDEX
    Explanations

    but, yet

    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
    èĢĮåIJĮ
    -0.10
    èĢĮéĻį
    -0.09
    è°´
    -0.08
    éĵ®
    -0.08
    èĢĮ以
    -0.08
    èĢĮä»İ
    -0.08
    ULD
    -0.07
     Enough
    -0.07
    éĵ¿
    -0.07
    åĨįä»İ
    -0.07
    POSITIVE LOGITS
    ased
    0.07
    ashi
    0.07
    èIJĥ
    0.06
     latter
    0.06
    ãĢģãĢģ
    0.06
    å±ħ
    0.06
    lard
    0.06
    eft
    0.06
    Broad
    0.06
    è¯ķçĤ¹å·¥ä½ľ
    0.06
    Activations Density 0.003%

    No Known Activations