© 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. 33731
    Prev
    Next
    INDEX
    Explanations

    area under, auc, below, exposure

    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
    orada
    -0.06
    æIJŃ
    -0.06
    St
    -0.06
    chow
    -0.06
    æ²¹çĽIJ
    -0.06
    Ħ
    -0.06
    蹬
    -0.05
    åIJĦçıŃ
    -0.05
    cline
    -0.05
    atural
    -0.05
    POSITIVE LOGITS
     Pey
    0.08
    漫漫
    0.08
     trá»įn
    0.08
    icans
    0.08
    èĩªå·±çļĦçĶŁåij½
    0.08
    ajian
    0.07
    omatis
    0.07
     вÑģÑİ
    0.07
    å°½æľī
    0.07
     باÙĦاÛĮ
    0.07
    Activations Density 0.004%

    No Known Activations