© 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. 33456
    Prev
    Next
    INDEX
    Explanations

    studies and research findings

    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¸įæ±Ĥ
    -0.08
     diesmal
    -0.07
    ukan
    -0.07
    ÑĢаÑĨиÑı
    -0.07
    <quote
    -0.07
    Raw
    -0.07
    åĴĮéĩįçĤ¹
    -0.07
     doGet
    -0.07
     دخ
    -0.07
    etur
    -0.07
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.14
     studies
    0.12
    çłĶ究æĺ¾ç¤º
    0.12
     Studies
    0.10
    çłĶ究åıijçİ°
    0.10
     иÑģÑģледований
    0.09
     research
    0.09
    udies
    0.09
    çłĶ究
    0.09
    Studies
    0.09
    Activations Density 0.628%

    No Known Activations