© 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. 17137
    Prev
    Next
    INDEX
    Explanations

    distant astronomical objects

    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
    太éĥİ
    -0.07
    _transform
    -0.07
    ivia
    -0.07
     subsequ
    -0.07
    yh
    -0.07
    anness
    -0.07
    transform
    -0.06
    awas
    -0.06
    ç«ĸåIJij
    -0.06
    对ä¸ĢäºĽ
    -0.06
    POSITIVE LOGITS
    åľ°çIJĥçļĦ
    0.09
    /send
    0.08
    éĥ½å¤Ħäºİ
    0.08
    åľ°çIJĥ
    0.08
     billions
    0.08
     Hoh
    0.07
    ullan
    0.07
    èĶļ
    0.07
     Earth
    0.07
     planet
    0.07
    Activations Density 0.002%

    No Known Activations