© 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. 57445
    Prev
    Next
    INDEX
    Explanations

    ‘ve been / started / first came

    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
    arro
    -0.08
    prat
    -0.08
    unk
    -0.08
    føl
    -0.08
     dolu
    -0.08
    رÙĬÙĨ
    -0.08
    Confirmed
    -0.07
    intang
    -0.07
    child
    -0.07
    FUNC
    -0.07
    POSITIVE LOGITS
    uhe
    0.06
    ↵
    0.06
     align
    0.06
     cab
    0.06
     intern
    0.06
    å¾ģéĢĶ
    0.05
    outh
    0.05
    ов
    0.05
     Decomp
    0.05
    æĭĸåĬ¨
    0.05
    Activations Density 0.007%

    No Known Activations