© 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. 51650
    Prev
    Next
    INDEX
    Explanations

    access or unlock

    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
    tober
    -0.07
    äv
    -0.07
    å¦ĤæľŁ
    -0.06
    po
    -0.06
    éĢĤ
    -0.06
    plin
    -0.06
    å¼¾
    -0.06
    å§Ķ
    -0.06
    å¿«èµ°
    -0.06
     Entw
    -0.06
    POSITIVE LOGITS
    æĭ¥æľīäºĨ
    0.09
     acceso
    0.08
     оÑĤÑĤ
    0.08
    åĽłä¸ºæľīäºĨ
    0.08
    rary
    0.08
    istö
    0.08
     access
    0.08
    via
    0.08
     acesso
    0.08
    AccessException
    0.07
    Activations Density 0.009%

    No Known Activations