© 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. 7890
    Prev
    Next
    INDEX
    Explanations

    initial words and phrases

    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
    ulik
    -0.10
    icol
    -0.08
    laub
    -0.08
    iom
    -0.07
    agra
    -0.07
    iloc
    -0.07
    etz
    -0.07
    aja
    -0.07
    ivil
    -0.06
    ocal
    -0.06
    POSITIVE LOGITS
    é¦ĸåħĪ
    0.09
    åħĪä»İ
    0.09
    é¦ĸåħĪæĺ¯
    0.09
     먼ìłĢ
    0.09
    먼
    0.08
     Ø£ÙĪÙĦاÙĭ
    0.08
     ìļ°ìĦł
    0.08
     firstly
    0.08
    é¦ĸåħĪåľ¨
    0.08
    ãģ¾ãģļ
    0.08
    Activations Density 0.192%

    No Known Activations