© 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. 49215
    Prev
    Next
    INDEX
    Explanations

    asking questions or seeking clarification

    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
    azes
    -0.06
    便
    -0.06
    è¿Ļå°±
    -0.06
    æ®Ĭ
    -0.06
     пÑĢиме
    -0.06
    é±¼
    -0.06
    çĽĪäºı
    -0.05
    زÙħ
    -0.05
    åºĥ
    -0.05
    agal
    -0.05
    POSITIVE LOGITS
    ä¸įè¦ģéĶĻè¿ĩ
    0.08
    ãĢıãĢİ
    0.08
    )ãĢģ
    0.08
    âĤ¬,
    0.08
    ä¸įèĥ½ä½ľä¸º
    0.08
    åıijåĪ°
    0.08
    ignon
    0.08
     минимÑĥм
    0.07
    enswert
    0.07
    ToLeft
    0.07
    Activations Density 0.007%

    No Known Activations