© 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. 50895
    Prev
    Next
    INDEX
    Explanations

    json-like structure or code snippets

    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
     poc
    -0.07
    æĸĮ
    -0.06
     Mensch
    -0.06
    ogi
    -0.06
    SPELL
    -0.06
    éºŁ
    -0.06
     Hass
    -0.06
    ãģĮåħ¥
    -0.06
    å¦ĤæŀľæĤ¨çļĦ
    -0.06
    <|box_end|>
    -0.06
    POSITIVE LOGITS
    å±ħ
    0.07
    presa
    0.07
    istar
    0.07
     Velo
    0.06
    entifier
    0.06
    anim
    0.06
    .functional
    0.06
    }@
    0.06
    康
    0.06
     CST
    0.06
    Activations Density 0.229%

    No Known Activations