© 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. 45696
    Prev
    Next
    INDEX
    Explanations

    job descriptions and details

    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
    landen
    -0.07
    .wikipedia
    -0.07
     Relevant
    -0.07
    kaç
    -0.06
    åłĤçļĩ
    -0.06
    ukai
    -0.06
    wich
    -0.06
    亢
    -0.06
    efined
    -0.06
     bá»Ļi
    -0.06
    POSITIVE LOGITS
    èĻ½å°ı
    0.08
    à¦Łà¦¿à¦°
    0.08
    åIJį称
    0.08
     name
    0.08
    spb
    0.08
    åIJį
    0.08
    åIJįãģ®
    0.08
    à¦Łà¦¿
    0.08
    çļĦè¿Ļä¸Ģ
    0.08
    éĢŁéĢĴ
    0.08
    Activations Density 0.565%

    No Known Activations