© 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. 25857
    Prev
    Next
    INDEX
    Explanations

    after, subsequently, later

    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
    ìķĺê³ł
    -0.07
    olg
    -0.07
    gni
    -0.07
    ä¸į以
    -0.07
    elus
    -0.07
    å°Ĩä»İ
    -0.06
     nämlich
    -0.06
    alia
    -0.06
    óre
    -0.06
     Kra
    -0.06
    POSITIVE LOGITS
     оÑĤÑĤ
    0.10
     thereafter
    0.10
     afterward
    0.10
     afterwards
    0.09
     subsequently
    0.09
     later
    0.09
     ÙĦاØŃÙĤ
    0.08
     ensuite
    0.08
     dần
    0.08
     thereof
    0.08
    Activations Density 0.223%

    No Known Activations