© 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. 41282
    Prev
    Next
    INDEX
    Explanations

    equal and opposite

    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
    inger
    -0.08
    ä¸įå¦Ĥ
    -0.08
     Locker
    -0.07
    enan
    -0.07
    intersection
    -0.07
    è¶Ĭæĺ¯
    -0.07
     intersection
    -0.07
    ogna
    -0.07
    jør
    -0.07
     intersections
    -0.07
    POSITIVE LOGITS
     cancel
    0.09
    æĬµæ¶Ī
    0.08
    ulses
    0.08
     cancelling
    0.08
     magnitude
    0.08
     canceled
    0.08
     exact
    0.08
     canc
    0.07
    é¢ĿçļĦ
    0.07
    Exact
    0.07
    Activations Density 0.005%

    No Known Activations