© 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. 40147
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
    ÑĥÑģа
    -0.08
    å°Ķçī¹
    -0.07
    åijµåijµ
    -0.07
    ä»ĸ乡
    -0.07
    ä½łåij¢
    -0.07
     teda
    -0.07
    äger
    -0.07
    ertz
    -0.07
    üe
    -0.07
    byname
    -0.07
    POSITIVE LOGITS
    ingan
    0.08
    åħ³äºİåģļ好
    0.08
    alani
    0.07
    วà¹Īาà¸ģาร
    0.07
    fi
    0.07
    à¸Ĥà¸Ńà¸ĩà¸Ħวาม
    0.06
     convainc
    0.06
     arról
    0.06
    åĬĽåº¦
    0.06
     Holl
    0.06
    Activations Density 0.039%

    No Known Activations