© 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. 29395
    Prev
    Next
    INDEX
    Explanations

    first person 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
    å±ħæĺĵ
    -0.09
    .bp
    -0.09
    ä½ľåģĩ
    -0.09
    vertise
    -0.09
    .Microsoft
    -0.08
    æĪ¿å¸Ĥ
    -0.08
    .Decode
    -0.08
    .Guid
    -0.08
    gnore
    -0.08
    __:
    -0.08
    POSITIVE LOGITS
    Âł
    0.06
    &
    0.06
     freaking
    0.06
    ...
    0.06
     fucking
    0.06
     you
    0.06
    åīĬ
    0.06
     anyway
    0.06
     your
    0.05
     ArgumentNullException
    0.05
    Activations Density 1.165%

    No Known Activations