© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58965
    Prev
    Next
    INDEX
    Explanations

    inverse

    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
    Negative Logits
    ebel
    -0.07
    madan
    -0.06
    anged
    -0.06
    è¶ħè¶Ĭ
    -0.06
    ông
    -0.06
    转转
    -0.06
    _logged
    -0.06
    åİĨéĻ©
    -0.06
    :+
    -0.06
    TEM
    -0.06
    POSITIVE LOGITS
    åĢĴæķ°
    0.11
    inverse
    0.10
    Inverse
    0.10
     inverse
    0.09
    .inverse
    0.09
    -inverse
    0.09
    _inverse
    0.08
    ylon
    0.08
     invers
    0.08
    .activ
    0.08
    Activations Density 0.001%

    No Known Activations