© 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. 62249
    Prev
    Next
    INDEX
    Explanations

    have, available, some

    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
    æľīäºĽåľ°æĸ¹
    -0.10
    æľīå¿Ĺ
    -0.10
    æľīåħ³äºĭ项
    -0.09
    æľīå¤ļå°ij人
    -0.08
    æľīå¿ĥ人
    -0.08
    acruz
    -0.08
    inach
    -0.08
    æľīå¤ļ大
    -0.08
    åĬªåĬĽä¸º
    -0.08
    ç»Ļ人çļĦ
    -0.08
    POSITIVE LOGITS
     recourse
    0.10
     access
    0.08
     knack
    0.08
     Anteil
    0.08
     enough
    0.08
     suficiente
    0.07
    æĦıè¯Ĩåľ°
    0.07
     been
    0.07
     koristi
    0.07
     доÑģÑĤÑĥпа
    0.07
    Activations Density 0.901%

    No Known Activations