© 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. 43172
    Prev
    Next
    INDEX
    Explanations

    word count and length

    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
    liga
    -0.08
    è§ģå¾Ĺ
    -0.07
    ÙĦÙĩ
    -0.07
    urig
    -0.07
     налиÑĩ
    -0.07
    ái
    -0.07
    edm
    -0.06
    è´±
    -0.06
    满天
    -0.06
    éĩİçĮª
    -0.06
    POSITIVE LOGITS
     paragraphs
    0.09
     sentences
    0.08
     prose
    0.08
    åIJĪçIJĨ使çĶ¨
    0.08
     hopefully
    0.08
     invol
    0.07
    迪äºļ
    0.07
    TION
    0.07
    åĨĻä¸Ģç¯ĩ
    0.07
     retra
    0.07
    Activations Density 0.024%

    No Known Activations