© 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. 64719
    Prev
    Next
    INDEX
    Explanations

    nonprecedential opinion

    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
    æī
    -0.07
    ил
    -0.06
    ä¸Ģå®ļ
    -0.06
    Ve
    -0.06
     erotisk
    -0.06
    ctor
    -0.06
    PRI
    -0.06
    жеÑĤÑģÑı
    -0.06
    çī©åĴĮ
    -0.06
    lvl
    -0.06
    POSITIVE LOGITS
    abi
    0.08
    å¦Ĥä¸Ĭ
    0.08
    çļĦè¿Ļä¸Ģ
    0.08
     tadi
    0.08
     aforementioned
    0.08
     Cliff
    0.08
    åīįè¿°
    0.07
     Cardoso
    0.07
     kaw
    0.07
    ä¸Ĭè¿°
    0.07
    Activations Density 0.036%

    No Known Activations