© 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. 27304
    Prev
    Next
    INDEX
    Explanations

    oxidases, statins, statements, views

    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
    DSA
    -0.08
    andie
    -0.08
    iasi
    -0.08
    anaan
    -0.07
    欢è¿İåħī临
    -0.07
    llx
    -0.07
    粪
    -0.07
    ULD
    -0.07
    Regions
    -0.07
    _EXTENSIONS
    -0.07
    POSITIVE LOGITS
    æŃ¤ä¸º
    0.08
    éļĨ
    0.07
    inqu
    0.06
    è¿Ļæĺ¯æĪij
    0.06
    ahui
    0.06
    åĨįåĬłä¸Ĭ
    0.06
     derived
    0.06
    å°±æĺ¯æĪijçļĦ
    0.06
    imon
    0.06
    erce
    0.06
    Activations Density 0.005%

    No Known Activations