© 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. 61923
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables

    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
    o
    -0.11
    åĬłæĭ¿å¤§
    -0.09
    æĸ°åĬłåĿ¡
    -0.08
    åĭĩå¾Ģ缴åīį
    -0.08
    æ¯Ľæ³½ä¸ľ
    -0.08
    ת
    -0.08
    en
    -0.08
    al
    -0.07
    an
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    POSITIVE LOGITS
    adays
    0.11
    èĩªå·±
    0.11
    köd
    0.10
    翼翼
    0.10
    efois
    0.09
    ÑĢовиÑĩ
    0.09
    resents
    0.09
    λοÏħ
    0.09
    agher
    0.09
    apun
    0.09
    Activations Density 0.031%

    No Known Activations