© 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. 3726
    Prev
    Next
    INDEX
    Explanations

    records for

    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
    ibble
    -0.08
    (ib
    -0.08
    ib
    -0.08
    ìŀİ
    -0.07
    -bodied
    -0.07
    ÛĮب
    -0.07
    htub
    -0.07
    Ïĥκ
    -0.07
    ihil
    -0.07
    aje
    -0.07
    POSITIVE LOGITS
    计
    0.07
     PMID
    0.07
    beck
    0.07
    ocas
    0.07
    éļıå¿ĥ
    0.06
     zas
    0.06
    åħĪçĶŁè¯´
    0.06
    åºĶäºİ
    0.06
    èİ«æµĭ
    0.06
    ikas
    0.06
    Activations Density 0.197%

    No Known Activations