© 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. 51289
    Prev
    Next
    INDEX
    Explanations

    new different altered formation

    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
    teman
    -0.08
    yaj
    -0.07
     McMahon
    -0.07
    chetto
    -0.07
    å°±å¤ŁäºĨ
    -0.07
    æij¸æ¸ħ
    -0.07
    placements
    -0.07
    æłĩåĩĨè¦ģæ±Ĥ
    -0.07
    Modes
    -0.07
    åħ¨è¦ĨçĽĸ
    -0.07
    POSITIVE LOGITS
    æĸ°çļĦ
    0.13
     new
    0.13
    æľīæĸ°çļĦ
    0.12
    åħ¨æĸ°çļĦ
    0.12
    åİŁæľī
    0.11
    æĶ¹åıĺ
    0.11
    æĶ¹åıĺäºĨ
    0.11
     ìĥĪë¡ľìļ´
    0.11
     altered
    0.11
    åħ¨æĸ°
    0.11
    Activations Density 0.017%

    No Known Activations