© 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. 21225
    Prev
    Next
    INDEX
    Explanations

    last_name

    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
    ä¸ĩéĩĮ
    -0.07
    åºĶ以
    -0.06
     (
    -0.06
     dec
    -0.06
     laboratory
    -0.06
    оло
    -0.05
     Laboratory
    -0.05
    ↵
    -0.05
    æĹ¥ä¸Ĭ
    -0.05
    .
    -0.05
    POSITIVE LOGITS
    hazi
    0.09
    &m
    0.08
    IFORM
    0.08
    viso
    0.08
    NgModule
    0.08
    zug
    0.08
    ä¹ŁæŃ£åľ¨
    0.08
    ارÙĬÙĨ
    0.08
    filt
    0.08
     exemp
    0.08
    Activations Density 0.002%

    No Known Activations