© 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. 46586
    Prev
    Next
    INDEX
    Explanations

    up and down

    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
    æľŁåĴĮ
    -0.09
    rawer
    -0.09
    .sax
    -0.09
    بار
    -0.09
    <|box_end|>
    -0.08
     اÙĦÙħبار
    -0.08
    SPATH
    -0.08
    ieb
    -0.08
    ibox
    -0.08
    agli
    -0.08
    POSITIVE LOGITS
     respectively
    0.12
    åĪĨåĪ«
    0.12
     alike
    0.11
    åIJĦæľī
    0.10
    ãģĿãĤĮãģŀãĤĮ
    0.09
    åĪĨåĪ«åľ¨
    0.09
    ãģĦãģļãĤĮ
    0.09
    åĪĨåĪ«æĺ¯
    0.08
    åIJĦèĩªçļĦ
    0.08
    åĪĨåĪ¥
    0.08
    Activations Density 0.129%

    No Known Activations