© 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. 45256
    Prev
    Next
    INDEX
    Explanations

    energy barrier

    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
     casc
    -0.08
     Casc
    -0.08
    éľĨ
    -0.07
    æ³ī
    -0.07
     cascade
    -0.07
    活水
    -0.07
     lát
    -0.06
    inet
    -0.06
    æĢ¡
    -0.06
     distrib
    -0.06
    POSITIVE LOGITS
     barrier
    0.09
     barriers
    0.09
    å£ģåŀĴ
    0.09
    Barrier
    0.09
     Barrier
    0.08
    Waiting
    0.08
    shield
    0.08
    ãĤŃãĥ¥
    0.08
    edan
    0.08
     shielding
    0.07
    Activations Density 0.002%

    No Known Activations