© 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. 33542
    Prev
    Next
    INDEX
    Explanations

    topic or issue

    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
    å®ĮæĪIJä»»åĬ¡
    -0.09
    æĢł
    -0.07
    ãĤ¶ãĥ¼
    -0.07
    è§ģçĬ¶
    -0.07
    çŃīä»Ģä¹Ī
    -0.07
     accompag
    -0.07
    æı©
    -0.07
    createForm
    -0.07
    kle
    -0.07
     Febbraio
    -0.07
    POSITIVE LOGITS
    è®®é¢ĺ
    0.18
    è¯Ŀé¢ĺ
    0.16
     topic
    0.16
     topics
    0.16
     issues
    0.15
    è¿Ļ个è¯Ŀé¢ĺ
    0.15
    èŃ°é¡Į
    0.15
     issue
    0.15
    çļĦè¯Ŀé¢ĺ
    0.14
    éĹ®é¢ĺæŶ
    0.14
    Activations Density 0.329%

    No Known Activations