© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 38143
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and parsing

    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
     Ñģебе
    -0.07
    åį
    -0.07
    volta
    -0.07
    raft
    -0.06
    她表示
    -0.06
    å¿ħ
    -0.06
    ONS
    -0.06
    ista
    -0.06
    zeh
    -0.06
    ä¸įå¦Ĥ
    -0.06
    POSITIVE LOGITS
    keit
    0.08
     {?}
    0.07
    ijker
    0.07
    egers
    0.07
    äufer
    0.07
    timeofday
    0.07
    amaha
    0.07
     TUY
    0.07
     Boll
    0.07
     YYS
    0.07
    Activations Density 0.001%

    No Known Activations