© 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. 63264
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    çĻ¾åĢį
    -0.07
    zana
    -0.07
    ായി
    -0.06
     سرد
    -0.06
    zar
    -0.06
    isty
    -0.06
    ļľ
    -0.06
     milione
    -0.06
    .ws
    -0.06
    åıijå±ķ为
    -0.06
    POSITIVE LOGITS
    0.09
    estate
    0.08
    ���
    0.07
    [table
    0.07
    {@
    0.07
    ests
    0.06
     
    0.06
    /[
    0.06
     perpetr
    0.06
    pend
    0.06
    Activations Density 0.257%

    No Known Activations