© 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. 60317
    Prev
    Next
    INDEX
    Explanations

    number sequences

    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
    äºĭä¸ļåıijå±ķ
    -0.07
    udid
    -0.07
    eer
    -0.07
    ykl
    -0.07
     Wonderland
    -0.07
    uppies
    -0.07
    .Op
    -0.06
    ä¸ī代
    -0.06
    entai
    -0.06
    æ²³ä¸ľ
    -0.06
    POSITIVE LOGITS
    kse
    0.08
    ong
    0.08
     getField
    0.07
    ä½Ĩå¦Ĥæŀľ
    0.07
    æĬ½å±ī
    0.07
    lis
    0.07
     intptr
    0.06
    ilas
    0.06
    stit
    0.06
    бини
    0.06
    Activations Density 0.002%

    No Known Activations