© 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. 27469
    Prev
    Next
    INDEX
    Explanations

    vertical position and scrolling

    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
    èĭ±ä¿Ĭ
    -0.13
     handsome
    -0.11
    çĪ¶åŃIJ
    -0.11
    å¸ħæ°Ķ
    -0.11
    å°ıåŃIJ
    -0.10
     himself
    -0.09
     masculinity
    -0.09
    å¸ħæ°ĶçļĦ
    -0.09
    大åıĶ
    -0.09
    éĺ³çĹ¿
    -0.09
    POSITIVE LOGITS
     vertical
    0.15
    vertical
    0.14
    (vertical
    0.14
    -vertical
    0.13
    Vertical
    0.13
     веÑĢÑĤика
    0.13
    åŀĤ缴
    0.13
     vertically
    0.12
    _vertical
    0.12
     verticale
    0.12
    Activations Density 0.119%

    No Known Activations