© 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. 38767
    Prev
    Next
    INDEX
    Explanations

    geographic segmentation

    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
    èħ±
    -0.08
     Legg
    -0.06
    åħ¨ç³»
    -0.06
    inado
    -0.06
    çĪĨ竹
    -0.06
    isar
    -0.06
    attan
    -0.06
    acket
    -0.06
     بذ
    -0.06
    纤
    -0.06
    POSITIVE LOGITS
     boundaries
    0.12
    åĪĴåĪĨ
    0.12
     overlapping
    0.11
     overlap
    0.11
     Assignment
    0.11
    overlap
    0.11
    Assign
    0.11
    éĩįåıł
    0.11
    Overlap
    0.11
    è¾¹çķĮ
    0.10
    Activations Density 0.036%

    No Known Activations