© 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. 7465
    Prev
    Next
    INDEX
    Explanations

    mathematical summation and products

    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
    _STD
    -0.08
    ILLE
    -0.07
     Sve
    -0.07
    对å®ĥ
    -0.07
     Sig
    -0.07
    å°½
    -0.07
    veld
    -0.06
    ç«Ł
    -0.06
    adio
    -0.06
    éĽ·é¸£
    -0.06
    POSITIVE LOGITS
    å½Ĵå±ŀäºİä¸Ĭå¸Ĥåħ¬åı¸
    0.07
    otive
    0.07
    ç¡®å®ļ为
    0.07
    驻马
    0.07
    angi
    0.07
     constraint
    0.07
    Forever
    0.07
    åıĪæĺ¯ä¸Ģå¹´
    0.07
    enville
    0.07
    åħ¬åı¸åIJij
    0.07
    Activations Density 0.004%

    No Known Activations