© 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. 39969
    Prev
    Next
    INDEX
    Explanations

    horror and haunting movies

    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
     bumper
    -0.08
    奢ä¾Ī
    -0.08
    ostar
    -0.07
     SpaceX
    -0.07
    nowrap
    -0.07
    ServiceProvider
    -0.07
    æĺķ
    -0.07
    åĩºå¾ģ
    -0.07
    æīĵæ°´
    -0.07
    ASAN
    -0.07
    POSITIVE LOGITS
    æ½ľä¼ı
    0.10
     haunting
    0.09
    æĥĬæĤļ
    0.09
     horror
    0.09
    åĩºæ²¡
    0.09
     lurking
    0.09
    éĺ´
    0.08
     Nec
    0.08
     manifestation
    0.08
     Horror
    0.08
    Activations Density 0.372%

    No Known Activations