© 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. 60287
    Prev
    Next
    INDEX
    Explanations

    event. time. tasks. change. era. size

    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
    ä¸ĭåIJĮ
    -0.07
    éļħ
    -0.07
     ï¼Ī
    -0.06
    å¾·åĪ©
    -0.06
    airs
    -0.06
    ...",
    -0.06
     (
    -0.06
    })",
    -0.06
    è§ij
    -0.06
    akta
    -0.06
    POSITIVE LOGITS
    çŁ¥éģĵèĩªå·±çļĦ
    0.08
    åİĨå±Ĭ
    0.08
     EVEN
    0.08
    ivic
    0.07
    åIJijåīįèµ°
    0.07
    ras
    0.07
    StringLength
    0.07
    åĩºå¥ĩ
    0.07
    ró
    0.07
    ANTE
    0.07
    Activations Density 0.002%

    No Known Activations