© 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. 29259
    Prev
    Next
    INDEX
    Explanations

    obtained from

    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
    eyond
    -0.08
    usercontent
    -0.07
    Ïĥμα
    -0.07
     ÐŁÐ¾Ð¿ÑĢо
    -0.07
    isEnabled
    -0.07
    ãĥĥãĤ±
    -0.07
    ä¸įäºĨ
    -0.07
    øv
    -0.07
    å¯Ĩå¯Ĩ
    -0.07
     gerade
    -0.07
    POSITIVE LOGITS
    éľ²
    0.08
     (;
    0.07
    èİ·èµł
    0.07
    (Material
    0.06
    ligen
    0.06
    ATERIAL
    0.06
     thaw
    0.06
    èĮľ
    0.06
    åĿĩéĩĩçĶ¨
    0.06
    ashes
    0.06
    Activations Density 0.501%

    No Known Activations