© 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. 62033
    Prev
    Next
    INDEX
    Explanations

    numbers in citations

    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
    ابÛĮ
    -0.07
    à¸ŀล
    -0.07
    åĶIJ人
    -0.07
    çѱ
    -0.07
    汶
    -0.07
    éĺ»çĩĥ
    -0.07
    åºĦ
    -0.07
    евиÑĩ
    -0.07
    aghan
    -0.07
    ursors
    -0.06
    POSITIVE LOGITS
    ud
    0.08
    åĨ²åĨ²
    0.07
    åĪĥ
    0.07
    olge
    0.07
    omot
    0.07
    NES
    0.07
    åĪĽåħĪäºīä¼ĺ
    0.07
    Mot
    0.06
    ä¾ĭè¡Į
    0.06
    WEB
    0.06
    Activations Density 0.020%

    No Known Activations