© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25173
    Prev
    Next
    INDEX
    Explanations

    2. description of the related art

    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
    åĿĤ
    -0.07
    å¥Ĺ
    -0.07
    γμα
    -0.07
    sein
    -0.07
    zus
    -0.07
    æ¸ħé¦Ļ
    -0.07
    akse
    -0.07
    ture
    -0.07
    akon
    -0.06
    zier
    -0.06
    POSITIVE LOGITS
    orem
    0.08
    orget
    0.07
    à¸Ńà¸Ķ
    0.07
    ormap
    0.07
    åĩłæ¬¾
    0.07
    é£Ľãģ°
    0.07
    ICOS
    0.07
    两款
    0.07
    èĤīçļĦ
    0.07
    产åĵģåıĬ
    0.07
    Activations Density 0.051%

    No Known Activations