© 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. 10988
    Prev
    Next
    INDEX
    Explanations

    legal / governmental / import / export

    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
    heim
    -0.08
     ÏĩÏģÏĮνο
    -0.08
    /locale
    -0.08
    rasil
    -0.08
     ...,
    -0.08
    acro
    -0.07
    Ïĥία
    -0.07
    eggia
    -0.07
    ê°Ī
    -0.07
    ecin
    -0.07
    POSITIVE LOGITS
    à¸Ķย
    0.07
    £
    0.07
    okrat
    0.06
    érc
    0.06
    ä¸Ģèµ·åIJĥ
    0.06
    è§ģçĬ¶
    0.06
    -fit
    0.06
    âij
    0.06
    ä¹³
    0.06
    Fit
    0.06
    Activations Density 0.017%

    No Known Activations