© 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. 34000
    Prev
    Next
    INDEX
    Explanations

    reverse direction

    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
    몰
    -0.07
    iz
    -0.07
    uz
    -0.07
    çĤ¹å¯¹çĤ¹
    -0.07
    ito
    -0.07
     Ñģвед
    -0.06
    ieke
    -0.06
    aktor
    -0.06
    pto
    -0.06
    裸
    -0.06
    POSITIVE LOGITS
    åıįåIJij
    0.16
     reverse
    0.16
    缸åıįçļĦ
    0.15
     Reverse
    0.15
     positive
    0.15
    è´ŁçļĦ
    0.15
    positive
    0.15
     reversed
    0.15
    éĢĨåIJij
    0.15
    缸åıį
    0.15
    Activations Density 0.137%

    No Known Activations