© 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. 9677
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation followed by text

    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
    ippy
    -0.08
    akah
    -0.07
    usch
    -0.07
    chaft
    -0.07
    erca
    -0.07
    é¡·
    -0.07
    hack
    -0.07
    arity
    -0.07
    WithPath
    -0.07
    retch
    -0.07
    POSITIVE LOGITS
    åĪ°æĤ¨
    0.07
    çĤ¹è¿Ľè¡Į
    0.07
    Ø°
    0.07
    serter
    0.07
    edException
    0.07
    .si
    0.07
    rung
    0.07
    uesa
    0.06
    MDB
    0.06
    身临åħ¶å¢ĥ
    0.06
    Activations Density 0.001%

    No Known Activations