© 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. 62126
    Prev
    Next
    INDEX
    Explanations

    mathematical derivatives

    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
    sez
    -0.08
    rikes
    -0.08
    oleon
    -0.08
    iau
    -0.07
    .Html
    -0.07
     ÐijезÑĥ
    -0.07
     ÐIJпÑĢе
    -0.07
    itations
    -0.07
    鼷鼨
    -0.07
    icch
    -0.07
    POSITIVE LOGITS
    orn
    0.06
    çIJIJ
    0.06
    idas
    0.06
    isman
    0.06
    对称
    0.06
     quart
    0.06
    rega
    0.06
    äºī
    0.05
    èģļ
    0.05
    äg
    0.05
    Activations Density 0.009%

    No Known Activations