© 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. 15583
    Prev
    Next
    INDEX
    Explanations

    home, must, at, off

    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
    ogos
    -0.08
    è·¡
    -0.08
    éľĸ
    -0.08
    ÙĩÙĨ
    -0.08
     Allem
    -0.07
    éĽ¾
    -0.07
    ablish
    -0.07
    afil
    -0.07
    umpt
    -0.07
    chers
    -0.07
    POSITIVE LOGITS
    leigh
    0.06
    æıIJåIJį
    0.06
    amb
    0.06
    strup
    0.06
    eld
    0.06
    anol
    0.06
    ity
    0.06
    çĶµè®¯
    0.06
     Wajib
    0.06
    tk
    0.06
    Activations Density 0.004%

    No Known Activations