© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23190
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and questions

    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
    /bower
    -0.07
     Giles
    -0.07
    rava
    -0.07
     much
    -0.06
    ulary
    -0.06
    èĢĮä¸ĭ
    -0.06
     kost
    -0.06
    _axes
    -0.06
    èĢĮè¿ĩ
    -0.06
    ..."
    -0.06
    POSITIVE LOGITS
    åijĹ
    0.09
     nai
    0.08
    оÑħ
    0.08
    ope
    0.07
    vely
    0.07
    écr
    0.07
    .bridge
    0.07
    è
    0.07
    ä¸įæĹ©
    0.07
    vel
    0.07
    Activations Density 0.020%

    No Known Activations