© 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. 22063
    Prev
    Next
    INDEX
    Explanations

    numbers and communication terms

    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
    ç¢İäºĨ
    -0.06
    atte
    -0.06
    ç¢İ
    -0.06
    使å®ĥ
    -0.06
     abroad
    -0.06
    åĨħåľ°
    -0.06
     respectively
    -0.06
     thái
    -0.06
    عا
    -0.06
    roph
    -0.06
    POSITIVE LOGITS
    usra
    0.09
    ...]
    0.08
    âĢ¦]
    0.08
    ||||
    0.08
    ---</
    0.08
    åĨįæİ¥åĨį
    0.08
    èĵ¬èݱ
    0.08
    è³ĩ
    0.07
    DDS
    0.07
    ]]></
    0.07
    Activations Density 0.002%

    No Known Activations