© 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. 48514
    Prev
    Next
    INDEX
    Explanations

    jury decisions and outcomes

    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
    åĬŀåħ¬
    -0.08
    ulk
    -0.08
     ìłķ리
    -0.07
    undur
    -0.07
    å¹³æ»ij
    -0.07
     smooth
    -0.07
     permohon
    -0.07
    å©¿
    -0.06
    umni
    -0.06
     accelerating
    -0.06
    POSITIVE LOGITS
    éĻªå®¡
    0.11
     jurors
    0.10
     acquitted
    0.09
     jury
    0.09
    éĻªå®¡åijĺ
    0.09
     Jury
    0.08
    åħ¬è¯ī
    0.08
     courtroom
    0.08
     Kraj
    0.08
     convict
    0.07
    Activations Density 0.085%

    No Known Activations