© 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. 28780
    Prev
    Next
    INDEX
    Explanations

    only followed by a noun

    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
     altrett
    -0.09
    unami
    -0.09
    edb
    -0.08
    esh
    -0.08
    деб
    -0.08
    echa
    -0.08
    heck
    -0.08
    öö
    -0.07
    дела
    -0.07
    åIJĦèĩªçļĦ
    -0.07
    POSITIVE LOGITS
     thing
    0.10
     viable
    0.10
     remaining
    0.09
    -ever
    0.09
     available
    0.09
     way
    0.09
     possible
    0.09
     ever
    0.09
    ä¹Łæĺ¯æľĢ
    0.08
     known
    0.08
    Activations Density 0.037%

    No Known Activations