© 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. 56283
    Prev
    Next
    INDEX
    Explanations

    name, agency, services, promises, modest

    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
     posix
    -0.06
    ä¹İ
    -0.06
    åį«çĶŁ
    -0.06
    ç»®
    -0.05
    reise
    -0.05
    _helpers
    -0.05
    纳
    -0.05
    eneuve
    -0.05
    asanya
    -0.05
    £
    -0.05
    POSITIVE LOGITS
    ymar
    0.09
    å·ħ
    0.08
    anmar
    0.07
    çĶ¨æĪ·åı¯ä»¥
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    allar
    0.07
    kees
    0.07
    sville
    0.07
    ãĤĬè¿Ķ
    0.07
    arts
    0.07
    Activations Density 0.005%

    No Known Activations