© 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. 26007
    Prev
    Next
    INDEX
    Explanations

    form, category, n, polynomials, grades

    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
    éĺ´
    -0.06
    andt
    -0.06
    ίκ
    -0.06
    çĥģ
    -0.06
    lese
    -0.06
    uttle
    -0.06
     credits
    -0.06
    estin
    -0.06
     running
    -0.06
    èij©
    -0.06
    POSITIVE LOGITS
    åIJĦ级
    0.12
    rade
    0.10
    ä¸įåIJĮç¨ĭ度
    0.10
    缴èĩ³
    0.10
    éĢIJ级
    0.09
    级
    0.09
    级åĪ«
    0.09
     grades
    0.09
    åĪĨ级
    0.09
     progressively
    0.09
    Activations Density 0.186%

    No Known Activations