© 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. 56446
    Prev
    Next
    INDEX
    Explanations

    semivolatile compounds

    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¸įå¹³
    -0.07
    istor
    -0.07
    addir
    -0.07
    æĮģå¹³
    -0.07
    ungan
    -0.07
    Ł
    -0.07
    ä¼Ĺ
    -0.07
    峪
    -0.07
    angkan
    -0.07
    æķijåij½
    -0.07
    POSITIVE LOGITS
    èĩ´
    0.08
    åIJĪéĢĤçļĦ
    0.07
    æľīè¶³å¤ŁçļĦ
    0.07
    ç¡®ä¿Ŀå®īåħ¨
    0.07
    è¶³å¤Ł
    0.07
     mild
    0.06
     fini
    0.06
    çĿ¡çĿĢäºĨ
    0.06
     sufficiently
    0.06
    ç¡®ä¿ĿäºĨ
    0.06
    Activations Density 0.017%

    No Known Activations