© 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. 19090
    Prev
    Next
    INDEX
    Explanations

    month, year, based, or, set

    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
    rastructure
    -0.08
    @example
    -0.07
    ÑĹв
    -0.07
    gunakan
    -0.06
    rechtliche
    -0.06
    äºĨåIJĹ
    -0.06
    artig
    -0.06
    -0.06
    bidden
    -0.06
    subclass
    -0.06
    POSITIVE LOGITS
    jenigen
    0.10
    /Delete
    0.09
    orem
    0.09
    ipment
    0.09
    -Col
    0.09
    -Year
    0.09
    -Based
    0.09
    -Fi
    0.09
    /Set
    0.09
     Himself
    0.09
    Activations Density 2.903%

    No Known Activations