© 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. 24558
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving numbers 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
    ë§ī
    -0.06
    izons
    -0.06
    sdale
    -0.06
    æŁ»
    -0.06
    iven
    -0.06
    ãĥ´
    -0.06
    éĺ»åĩ»æĪĺ
    -0.06
    utton
    -0.06
     Pruitt
    -0.06
    åıĸèĩª
    -0.06
    POSITIVE LOGITS
    çĥ¦
    0.08
    ondi
    0.07
    aren
    0.07
    æķ£
    0.07
    oure
    0.07
    以å¾Į
    0.07
    ory
    0.07
    åIJĪ家
    0.07
    Assembler
    0.07
    诸
    0.07
    Activations Density 0.013%

    No Known Activations