© 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. 64601
    Prev
    Next
    INDEX
    Explanations

    divisible by, term of

    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
    asanya
    -0.08
    azin
    -0.08
    èij«èĬ¦
    -0.07
    娲
    -0.07
    ä½łçľŁçļĦ
    -0.07
     priz
    -0.07
    Exposed
    -0.07
    Socket
    -0.07
    ä¸Ģåī¯
    -0.07
    ä¸Ģ转
    -0.07
    POSITIVE LOGITS
    ç¿»
    0.06
    æģ°
    0.06
    æģ°å¥½
    0.06
    odom
    0.06
    _tim
    0.06
    æģ°åĪ°
    0.06
    åĪļåĪļ好
    0.06
     ternyata
    0.06
    eshire
    0.06
    reb
    0.06
    Activations Density 0.026%

    No Known Activations