© 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. 50687
    Prev
    Next
    INDEX
    Explanations

    isolation, confinement, or separateness

    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
    解åĨ»
    -0.07
    ibar
    -0.07
    çģµåĬ¨
    -0.07
    éľĸ
    -0.07
    çģµæ´»
    -0.07
    æĹłæĥħ
    -0.06
    对å¾ħ
    -0.06
    rophe
    -0.06
     NU
    -0.06
    vester
    -0.06
    POSITIVE LOGITS
    å°ģéĹŃ
    0.15
     isolated
    0.15
    éļĶç»Ŀ
    0.15
    å°ģéĹŃå¼ı
    0.14
    å±ĢéĻIJäºİ
    0.14
     isolation
    0.14
    éĹŃéŨ
    0.13
     izol
    0.13
     confines
    0.13
     isol
    0.13
    Activations Density 0.199%

    No Known Activations