© 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. 39085
    Prev
    Next
    INDEX
    Explanations

    precedent and binding

    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
    atar
    -0.09
    queo
    -0.08
    被æįķ
    -0.08
    é»Ħ页
    -0.08
    ugas
    -0.08
    <|box_end|>
    -0.07
    ayani
    -0.07
    á»IJ
    -0.07
    ebut
    -0.07
    ìĶ¨
    -0.07
    POSITIVE LOGITS
     binding
    0.10
    æķĪåĬĽ
    0.10
    çĶŁæķĪ
    0.09
    æķĪåĬĽçļĦ
    0.08
    æ³ķå¾ĭæķĪåĬĽ
    0.08
    binding
    0.08
    åIJĮçŃī
    0.08
     Binding
    0.08
    -binding
    0.08
    /sign
    0.08
    Activations Density 0.061%

    No Known Activations