© 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. 42281
    Prev
    Next
    INDEX
    Explanations

    superposition of states

    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
    asc
    -0.08
    ASP
    -0.07
     Segu
    -0.07
    ril
    -0.07
    rics
    -0.07
    ÃŃ
    -0.07
    sworth
    -0.07
     eskort
    -0.07
    tek
    -0.06
    ières
    -0.06
    POSITIVE LOGITS
    æĢģ
    0.09
    çĬ¶æĢģçļĦ
    0.08
    çĬ¶æĢģ
    0.08
     states
    0.07
    edas
    0.07
    æħĭ
    0.07
    ozy
    0.07
    çĬ¶æħĭãģ§
    0.07
    tures
    0.07
     estados
    0.07
    Activations Density 0.002%

    No Known Activations