© 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. 26492
    Prev
    Next
    INDEX
    Explanations

    room or Room

    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
    ocities
    -0.09
    eder
    -0.09
    ively
    -0.09
    <|box_end|>
    -0.08
    ÙĪرÙĬا
    -0.08
    erez
    -0.07
     Trafford
    -0.07
    Ķ
    -0.07
    upeÅĤ
    -0.07
    cope
    -0.07
    POSITIVE LOGITS
    åħ§çļĦ
    0.09
    åĨħçļĦ
    0.08
    liness
    0.08
    à¹Ģà¸Ľà¸¥à¹Īา
    0.07
    mates
    0.07
    ful
    0.07
    lain
    0.07
    itsu
    0.07
    主任
    0.07
    -door
    0.07
    Activations Density 0.083%

    No Known Activations