© 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. 38452
    Prev
    Next
    INDEX
    Explanations

    likely, probably, possible

    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
    agens
    -0.09
     Rekord
    -0.08
    ouver
    -0.08
    åĽłä¸ºæ²¡æľī
    -0.08
    uas
    -0.08
    天æīį
    -0.07
    çĶ±äºİåħ¶
    -0.07
     ersta
    -0.07
    ulary
    -0.07
    _RESP
    -0.07
    POSITIVE LOGITS
     lay
    0.07
     likely
    0.07
    æľīä¸Ģçķª
    0.07
    大æ¦Ĥçİĩ
    0.06
    éģ¿
    0.06
    likely
    0.06
    ray
    0.06
    forth
    0.06
    èİ«åıĬ
    0.06
    æľīæīĢ
    0.06
    Activations Density 0.037%

    No Known Activations