© 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. 18946
    Prev
    Next
    INDEX
    Explanations

    third derivative, pride, difficulty

    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
    ÑģÑĢе
    -0.07
    оÑĩе
    -0.07
    EFE
    -0.06
    ÑĢÑĥд
    -0.06
    eny
    -0.06
    dy
    -0.06
    éĽĨ
    -0.06
    asters
    -0.06
    çŃı
    -0.06
    AFE
    -0.06
    POSITIVE LOGITS
    天ä¸ĭçļĦ
    0.07
    erc
    0.07
    åħ°è¾¾
    0.07
    instanc
    0.07
    alc
    0.07
    翼翼
    0.07
    arkin
    0.07
    angu
    0.07
    alon
    0.07
    -md
    0.07
    Activations Density 0.202%

    No Known Activations