© 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. 46280
    Prev
    Next
    INDEX
    Explanations

    size and scale units

    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
     unequal
    -0.07
     imperfect
    -0.07
    alej
    -0.07
     Huang
    -0.06
    ino
    -0.06
    èĢĮçŁ¥
    -0.06
    ä¸Ģè¨Ģ
    -0.06
    ¤
    -0.06
    æĿijæĿij
    -0.06
    _SEQ
    -0.06
    POSITIVE LOGITS
    -scale
    0.09
    Scaler
    0.08
    cope
    0.08
    scale
    0.08
    INLINE
    0.08
     scale
    0.08
     Scale
    0.08
     handl
    0.07
    Scale
    0.07
    inator
    0.07
    Activations Density 0.005%

    No Known Activations