© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29941
    Prev
    Next
    INDEX
    Explanations

    recently opened or saved

    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
     unless
    -0.08
    edException
    -0.08
     wanneer
    -0.08
     tomorrow
    -0.08
     Unless
    -0.08
    unless
    -0.08
    ers
    -0.07
     derzeit
    -0.07
    éĻ¤éĿŀ
    -0.07
     upcoming
    -0.07
    POSITIVE LOGITS
     volna
    0.16
     recentemente
    0.13
     вÑĩеÑĢа
    0.12
    Successfully
    0.11
     gestern
    0.10
     recientemente
    0.10
    ãģ°ãģĭãĤĬ
    0.10
     succesfully
    0.10
     recently
    0.10
     récemment
    0.10
    Activations Density 0.794%

    No Known Activations