© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    excited singlet states

    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
    æĸ½å·¥æĬĢæľ¯
    -0.07
    çĶ¨æĸĻ
    -0.07
    åĿĩè¡¡
    -0.07
    åºĻ
    -0.07
    ceph
    -0.07
    åĽłåħ¬
    -0.06
    éĶ¡
    -0.06
    fft
    -0.06
    è¿ľæľŁ
    -0.06
    zag
    -0.06
    POSITIVE LOGITS
    Clr
    0.10
    /photo
    0.09
    红å®ĿçŁ³
    0.08
     excited
    0.08
    åıijåħī
    0.08
     Resorts
    0.07
     molecule
    0.07
     photoc
    0.07
    åľĺ
    0.07
    çĮĿ
    0.07
    Activations Density 0.034%

    No Known Activations