© 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. 7937
    Prev
    Next
    INDEX
    Explanations

    itself, themselves, invariant

    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
    ä¸Ĭè¿Ľå¿ĥ
    -0.08
    为贯彻èIJ½å®ŀ
    -0.08
    Abr
    -0.08
    ÏĥÏĦή
    -0.08
     Acu
    -0.08
    顺åĪ©
    -0.07
    lein
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    wares
    -0.07
    cluded
    -0.07
    POSITIVE LOGITS
    rot
    0.08
     unchanged
    0.08
    ä¿ĿæĮģä¸įåıĺ
    0.08
    oyer
    0.07
    å¢ŀåĩı
    0.07
     rotated
    0.07
    æĹĭ转
    0.07
     invariant
    0.07
    Invariant
    0.07
     Rot
    0.06
    Activations Density 0.007%

    No Known Activations