© 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. 61464
    Prev
    Next
    INDEX
    Explanations

    this, from, _id, testing, Mage, resource

    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
    upi
    -0.07
    åĪĨå¤ĸ
    -0.07
    æĹłæ°´
    -0.07
    azines
    -0.06
    iki
    -0.06
    æľīä¸į
    -0.06
    åı¯åı¯
    -0.06
    fy
    -0.06
    rus
    -0.06
    天åIJİ
    -0.06
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.13
     rather
    0.12
    èĢĮéĿŀ
    0.12
    rather
    0.10
     plutôt
    0.10
     chứ
    0.09
     statt
    0.09
     Rather
    0.08
    ule
    0.08
     instead
    0.08
    Activations Density 0.030%

    No Known Activations