© 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. 27904
    Prev
    Next
    INDEX
    Explanations

    2 year specifications

    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
    ÑĢоли
    -0.08
    ikit
    -0.07
    ambo
    -0.07
    aro
    -0.07
    ijker
    -0.07
    icola
    -0.07
    âķIJâķIJ
    -0.06
    inii
    -0.06
    laud
    -0.06
    .nodeType
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥĦ
    0.07
    astia
    0.07
    åIJijåIJİ
    0.07
    lsa
    0.07
    _RESOURCES
    0.07
    lein
    0.07
    大åĪ©
    0.06
    转让人
    0.06
    èݫ大çļĦ
    0.06
    afa
    0.06
    Activations Density 0.001%

    No Known Activations