© 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. 18513
    Prev
    Next
    INDEX
    Explanations

    rather

    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
    _UNICODE
    -0.08
    lej
    -0.07
    .native
    -0.07
    ickle
    -0.07
    mozilla
    -0.07
    èĥŃèĦĤ
    -0.07
    FIX
    -0.07
     Brock
    -0.07
    ÏģοÏĨο
    -0.07
    gup
    -0.06
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.10
    —not
    0.09
    èĢĮéĿŀ
    0.09
     rather
    0.09
    ä¸Ģè¯į
    0.08
     chứ
    0.08
    äºĮåŃĹ
    0.08
    æĮĩçļĦæĺ¯
    0.07
    rather
    0.07
     Rather
    0.07
    Activations Density 0.062%

    No Known Activations