© 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. 56430
    Prev
    Next
    INDEX
    Explanations

    calibration

    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
    hood
    -0.09
    çĹĩ
    -0.07
    fully
    -0.07
    lichkeit
    -0.07
    ful
    -0.07
    halb
    -0.07
    iveness
    -0.06
    veld
    -0.06
    รà¹īาย
    -0.06
    alis
    -0.06
    POSITIVE LOGITS
     ulang
    0.11
    ibrated
    0.09
    ibrate
    0.09
    ibration
    0.09
    rection
    0.08
    /testing
    0.08
    /cal
    0.08
    achter
    0.08
     setC
    0.08
    éĢļãĤĬãģ«
    0.08
    Activations Density 0.047%

    No Known Activations