© 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. 27070
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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§ŀ
    -0.07
     vX
    -0.07
    ¹
    -0.06
    دار
    -0.06
    .pb
    -0.06
    ±
    -0.06
    å±ħæ°ij身份è¯ģ
    -0.06
    åĴĮ社ä¼ļä¿Ŀéļľ
    -0.06
    enea
    -0.06
     suck
    -0.06
    POSITIVE LOGITS
    lei
    0.08
    stat
    0.08
    ç¿Ł
    0.08
    attes
    0.07
    çĬ
    0.07
    erea
    0.07
    Arte
    0.07
    ç¼Ń
    0.07
    _placement
    0.07
    ç´
    0.07
    Activations Density 0.003%

    No Known Activations