© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17536
    Prev
    Next
    INDEX
    Explanations

    author, image, or .md file paths

    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
    UDGE
    -0.08
    tiny
    -0.07
    Ñģев
    -0.07
    loff
    -0.07
    åİ»ä½ķ
    -0.07
    strand
    -0.07
    对æѤä¸įæī¿æĭħä»»ä½ķ
    -0.07
    upe
    -0.07
    _md
    -0.07
    æ°¨éħ¸
    -0.07
    POSITIVE LOGITS
    (s
    0.12
    æĪĸå¤ļ个
    0.09
    们éĥ½
    0.09
    (es
    0.08
    们
    0.07
    æĹłæŀģ
    0.07
    åĪģ
    0.07
    bogen
    0.07
    [s
    0.07
    以åıĬåħ¶ä»ĸ
    0.07
    Activations Density 0.912%

    No Known Activations