© 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. 29368
    Prev
    Next
    INDEX
    Explanations

    fraction expressions

    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
    teg
    -0.07
    anches
    -0.07
    nene
    -0.07
    eneg
    -0.07
    æĮºèĥ¸
    -0.06
    à§įত
    -0.06
    legate
    -0.06
    ANEL
    -0.06
    ené
    -0.06
    aneously
    -0.06
    POSITIVE LOGITS
    ick
    0.08
    itzer
    0.08
    ackbar
    0.08
    ickle
    0.08
    oc
    0.08
     PACKET
    0.07
    ocu
    0.07
    acking
    0.07
    amespace
    0.07
    StringValue
    0.07
    Activations Density 0.006%

    No Known Activations