© 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. 33386
    Prev
    Next
    INDEX
    Explanations

    number "6" or size

    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
    è¿Ļä¸Ģ
    -0.07
    “
    -0.07
    ‘
    -0.06
    ,
    -0.06
    ...
    -0.06
    "
    -0.06
    in
    -0.06
    ...).
    -0.06
    v
    -0.06
    CP
    -0.06
    POSITIVE LOGITS
    (optional
    0.08
    翼翼
    0.08
    ardım
    0.08
    ål
    0.08
    schlä
    0.08
    modele
    0.08
    ÄĻk
    0.08
    åıĬè¦ģæ±Ĥ
    0.08
    ÄĻg
    0.08
    à¸Ńลลà¹Į
    0.08
    Activations Density 0.002%

    No Known Activations