© 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. 56412
    Prev
    Next
    INDEX
    Explanations

    list or array indices

    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
    ÏĦÏģ
    -0.07
    rys
    -0.06
    ips
    -0.06
    azu
    -0.06
    å¢ĥçļĦ
    -0.06
     оз
    -0.06
    Spl
    -0.06
     altern
    -0.06
     Cath
    -0.06
    iah
    -0.06
    POSITIVE LOGITS
    è°ģéĥ½
    0.07
    usada
    0.07
    严äºİ
    0.07
    çĵ®
    0.07
    Æ¡
    0.07
    ä½łåij¢
    0.07
    grid
    0.07
    anson
    0.07
    xEC
    0.07
    åĪĨ级
    0.07
    Activations Density 0.025%

    No Known Activations