© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29806
    Prev
    Next
    INDEX
    Explanations

    string format conversions

    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
     cáºŃn
    -0.07
    好äºĭ
    -0.07
    åĩºåĽ½
    -0.06
    hiri
    -0.06
     fiss
    -0.06
     Patri
    -0.06
    teras
    -0.06
    ä¸ĢçĶŁ
    -0.06
    æį·
    -0.06
    _matching
    -0.06
    POSITIVE LOGITS
    éľĢè¦ģåħĪ
    0.11
    .Convert
    0.09
    converted
    0.08
    æīĢ以è¦ģ
    0.08
    éľĢè¦ģç»ıè¿ĩ
    0.08
    è¦ģåħĪ
    0.08
    转æį¢æĪIJ
    0.08
    umed
    0.08
    _convert
    0.08
    raw
    0.08
    Activations Density 0.140%

    No Known Activations