© 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. 23260
    Prev
    Next
    INDEX
    Explanations

    math and code contexts

    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
    å¸ĺ
    -0.07
    åĮºå§Ķ书记
    -0.07
    eer
    -0.06
    å¤į
    -0.06
    å¹³åİŁ
    -0.06
     Lim
    -0.06
    èij«
    -0.06
    erate
    -0.06
    lim
    -0.06
     lim
    -0.06
    POSITIVE LOGITS
    ck
    0.08
    jaz
    0.07
    ends
    0.07
     lands
    0.07
    unge
    0.07
    ospel
    0.07
    _times
    0.07
    uffle
    0.07
    ui
    0.07
    esting
    0.07
    Activations Density 0.004%

    No Known Activations