© 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. 27321
    Prev
    Next
    INDEX
    Explanations

    mathematical notation arrows

    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
    äºĨ
    -0.07
    àºĩ
    -0.07
    inal
    -0.07
    inals
    -0.06
    ynthia
    -0.06
     оÑĤмеÑĤ
    -0.06
    acre
    -0.06
    1
    -0.06
    chied
    -0.06
    INAL
    -0.06
    POSITIVE LOGITS
    olly
    0.09
    ouden
    0.09
    oyer
    0.09
    ród
    0.08
    óÅĤ
    0.08
     ÑĤаки
    0.08
    éĻĦä¸Ń
    0.08
    acl
    0.08
    Produk
    0.08
    ij
    0.07
    Activations Density 0.031%

    No Known Activations