© 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. 60493
    Prev
    Next
    INDEX
    Explanations

    direction reversal

    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
     Horizonte
    -0.09
    ÐĿÐļ
    -0.09
    edig
    -0.08
     ekstrak
    -0.08
    æŃ¤æ¥¼
    -0.08
    å¾ĭå¸Ī解çŃĶ
    -0.08
    æľĪä¸Ń
    -0.08
    ä¸į好äºĨ
    -0.08
     ninh
    -0.08
    ToInt
    -0.07
    POSITIVE LOGITS
    åıį转
    0.13
     reversing
    0.13
     reversal
    0.13
    缸åıįçļĦ
    0.13
    é¢łåĢĴ
    0.13
     opposite
    0.13
     reversed
    0.12
     convention
    0.12
     conventions
    0.12
     Convention
    0.11
    Activations Density 0.018%

    No Known Activations