© 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. 50250
    Prev
    Next
    INDEX
    Explanations

    of values, maximum, converted, generated, valid

    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
    éĽĨè®Ń
    -0.08
    enville
    -0.07
    tui
    -0.07
     Canyon
    -0.07
    åľ¨ä¸ĭè½½
    -0.07
    olik
    -0.07
    ehen
    -0.07
    两å¤Ħ
    -0.07
     Lagu
    -0.07
    èħ¾è®¯è§Ĩé¢ij
    -0.07
    POSITIVE LOGITS
     whatever
    0.08
    whatever
    0.07
    Whatever
    0.07
    vene
    0.07
     Whatever
    0.07
    —including
    0.07
    ç¥ŀçļĦ
    0.06
    verb
    0.06
    isi
    0.06
    ursive
    0.06
    Activations Density 0.006%

    No Known Activations