© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32997
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    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
    itional
    -0.09
    OrUpdate
    -0.09
    cing
    -0.08
    /column
    -0.08
    eneric
    -0.08
    ading
    -0.08
    aming
    -0.08
     ÑĤаки
    -0.08
    hoc
    -0.08
    kinson
    -0.08
    POSITIVE LOGITS
     باÙĦÙĦÙĩ
    0.10
    éĩįéĩįçļĦ
    0.10
    éĩįéĩį
    0.08
    /error
    0.08
    iegen
    0.08
    ainties
    0.08
    æĪĸ缺
    0.08
    uries
    0.08
    /dis
    0.08
    ä¸įåĨ³
    0.08
    Activations Density 0.010%

    No Known Activations