© 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. 40228
    Prev
    Next
    INDEX
    Explanations

    probes or emitters of light/fields

    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
    umont
    -0.07
    abi
    -0.06
    æī¿
    -0.06
    omis
    -0.06
    æѦèĢħ
    -0.06
    èĬ±
    -0.06
    ELY
    -0.06
    æѦ
    -0.06
    åı£æ°´
    -0.06
    ous
    -0.06
    POSITIVE LOGITS
    probe
    0.12
     probe
    0.11
     probes
    0.11
     probing
    0.11
    æİ¢éĴĪ
    0.10
    ä¸İ被
    0.10
    Probe
    0.10
     Probe
    0.10
     dò
    0.09
    æİ¢æµĭ
    0.09
    Activations Density 0.148%

    No Known Activations