© 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. 20160
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    менÑĥ
    -0.10
    tida
    -0.09
    大å¹ħ度
    -0.09
    ague
    -0.08
    ytu
    -0.08
    одно
    -0.08
    æľīæѤ
    -0.08
    hani
    -0.08
    겸
    -0.08
    jera
    -0.08
    POSITIVE LOGITS
    ish
    0.09
    imal
    0.06
    اء
    0.06
    ,
    0.06
    .
    0.06
    ified
    0.06
    иÑĤаÑĢ
    0.06
     or
    0.06
    -
    0.06
    0
    0.06
    Activations Density 0.052%

    No Known Activations