© 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. 62860
    Prev
    Next
    INDEX
    Explanations

    accumulation of sums

    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
    毫ä¸įçĬ¹è±«
    -0.08
    åĢĻéĢī
    -0.08
    Ø´Ùħ
    -0.08
    รà¸Ńà¸ĩ
    -0.07
     pisc
    -0.07
    ihu
    -0.07
    INCLUDING
    -0.07
    ازÙĦ
    -0.07
    毫ä¸įçĬ¹è±«åľ°
    -0.07
    æ¹Ľ
    -0.07
    POSITIVE LOGITS
    èijĽ
    0.07
     accumulation
    0.07
    _accum
    0.07
     Reich
    0.07
     accumulating
    0.07
    ItemCount
    0.07
    ãĥĪãĥ©
    0.06
     Ca
    0.06
    accum
    0.06
     Kum
    0.06
    Activations Density 0.001%

    No Known Activations