© 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. 4428
    Prev
    Next
    INDEX
    Explanations

    constitutional amendment rights

    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
    czo
    -0.09
    ocr
    -0.09
    ÅĤow
    -0.08
    ROUT
    -0.08
    å±ħæĺĵ
    -0.08
    éģĩ
    -0.08
    _MA
    -0.07
    timi
    -0.07
    èī²åĪĹ
    -0.07
    iore
    -0.07
    POSITIVE LOGITS
    scher
    0.07
    ฯ
    0.06
     Hard
    0.06
    eyer
    0.06
     Society
    0.06
    ak
    0.06
    landers
    0.06
    rant
    0.06
    blink
    0.05
     dÃłnh
    0.05
    Activations Density 0.011%

    No Known Activations