© 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. 30402
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with constants 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
    scha
    -0.08
     Wanted
    -0.07
    antor
    -0.07
    _fifo
    -0.07
    vae
    -0.07
    |string
    -0.07
    çĻ½äºĨ
    -0.07
     Retrou
    -0.07
    bem
    -0.07
    èĭį天
    -0.06
    POSITIVE LOGITS
    ä¸į说
    0.07
    æŀķ
    0.07
    æľĪåľĨ
    0.07
    _consts
    0.07
    ulare
    0.06
    该类
    0.06
    就说
    0.06
     Pej
    0.06
     limp
    0.06
    æĸ§
    0.06
    Activations Density 0.008%

    No Known Activations