© 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. 3035
    Prev
    Next
    INDEX
    Explanations

    THINK IT

    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
    ienes
    -0.09
    ”âĢ¦
    -0.08
    endah
    -0.08
    нÑģ
    -0.08
    .']
    -0.08
    ela
    -0.08
    ÑĤÑĩ
    -0.08
    +"]
    -0.08
    !»
    -0.08
    _mgmt
    -0.08
    POSITIVE LOGITS
    0.07
     ↵
    0.06
    0.06
    åħ¶èº«
    0.06
    red
    0.06
    Ì
    0.06
    0.06
    0.06
    **
    0.06
    0.06
    Activations Density 0.240%

    No Known Activations