© 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. 9904
    Prev
    Next
    INDEX
    Explanations

    `@` and `#!/`

    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
    iebe
    -0.08
    eli
    -0.08
    chini
    -0.08
    icola
    -0.08
    иÑİ
    -0.08
    icz
    -0.08
    踵
    -0.07
    ilien
    -0.07
    à§įত
    -0.07
    æ±Ģ
    -0.07
    POSITIVE LOGITS
    jenigen
    0.10
    缸è¾ħ缸æĪIJ
    0.08
    åĴĮ
    0.08
    a
    0.08
    sWith
    0.08
    ĥ
    0.08
    c
    0.07
    ł
    0.07
    ona
    0.07
    ly
    0.07
    Activations Density 0.002%

    No Known Activations