© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14728
    Prev
    Next
    INDEX
    Explanations

    numbers followed by counts

    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
    åĩłæŃ¥
    -0.07
    .comp
    -0.07
    æĺ¯å¾Ī
    -0.07
     ÑģÑĤолк
    -0.07
    erecht
    -0.07
    itam
    -0.07
    edt
    -0.07
    protocol
    -0.07
    è¿Ļç§įä¸ľè¥¿
    -0.07
    å¹´å¤ļ
    -0.06
    POSITIVE LOGITS
     remaining
    0.10
    remaining
    0.10
     restantes
    0.08
     kia
    0.08
     aforementioned
    0.07
     dintre
    0.07
    -plus
    0.07
    eline
    0.07
    rette
    0.06
     chosen
    0.06
    Activations Density 0.205%

    No Known Activations