© 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. 21750
    Prev
    Next
    INDEX
    Explanations

    list item introductions

    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
    hiba
    -0.08
    adou
    -0.08
    åIJ¦åĪĻ
    -0.08
    aan
    -0.08
    arat
    -0.07
    anis
    -0.07
    हार
    -0.07
    urm
    -0.07
     Materiale
    -0.07
    åħ¶ä¸Ń
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.12
    \.
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    åĩ¡æľ¬ç½ij注æĺİ
    0.07
    oth
    0.06
     Core
    0.06
     Redistributions
    0.06
    ongs
    0.06
    째
    0.06
    º
    0.06
    Activations Density 0.022%

    No Known Activations