© 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. 62789
    Prev
    Next
    INDEX
    Explanations

    units and variables

    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
    -handler
    -0.07
    ULE
    -0.07
    -www
    -0.06
    åı°
    -0.06
    Wunused
    -0.06
    aber
    -0.06
    à¸ģำà¹Ģà¸Ļิà¸Ķ
    -0.06
    alink
    -0.06
    nap
    -0.06
    èĩº
    -0.06
    POSITIVE LOGITS
    æ²³éĩĮ
    0.09
     konst
    0.07
     Amend
    0.07
    angg
    0.07
     Arts
    0.07
    ibr
    0.07
    untime
    0.07
    rapper
    0.07
    驱
    0.07
    ìº
    0.07
    Activations Density 0.132%

    No Known Activations