© 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. 41940
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

    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
    enin
    -0.07
    èݲèĹķ
    -0.07
    çī©æµģä¸Ńå¿ĥ
    -0.07
     fico
    -0.06
    Ùħر
    -0.06
     pire
    -0.06
    esai
    -0.06
    arkin
    -0.06
    à¸ģ
    -0.06
    اØŃÙĨ
    -0.06
    POSITIVE LOGITS
    ä¸įè´Ł
    0.08
     itemView
    0.08
    èģĮåĬ¡
    0.07
    ظÛĮÙħ
    0.07
    éĶ¦æłĩ
    0.07
    ä¸īçķĮ
    0.07
    _restrict
    0.07
    æĽĻ
    0.07
    inas
    0.07
    ä¸įæħİ
    0.07
    Activations Density 0.113%

    No Known Activations