© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17945
    Prev
    Next
    INDEX
    Explanations

    testing, output, return

    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
    æ¢ĵ
    -0.07
    çļĦå¤ĸéĥ¨
    -0.07
    سÙĪ
    -0.07
    Wil
    -0.07
    ten
    -0.07
     Wil
    -0.07
    itano
    -0.07
    aho
    -0.07
     ëĶ°
    -0.07
    uda
    -0.07
    POSITIVE LOGITS
    ingleton
    0.08
    oglio
    0.07
     Ridley
    0.06
    NullOr
    0.06
    éľĸ
    0.06
    iehen
    0.06
    finder
    0.06
    èĢģå°ij
    0.06
    åħ·ä½ĵåĨħ容
    0.06
    houd
    0.06
    Activations Density 0.001%

    No Known Activations