© 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. 48713
    Prev
    Next
    INDEX
    Explanations

    former, latter, first, last, both

    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
    æĭīå°Ķ
    -0.07
    nard
    -0.07
    lak
    -0.07
    nsk
    -0.07
    ontre
    -0.07
    assistant
    -0.07
    igy
    -0.07
    andi
    -0.07
    Ł
    -0.07
    BuilderFactory
    -0.06
    POSITIVE LOGITS
    两èĢħ
    0.17
    åIJİèĢħ
    0.17
    åīįèĢħ
    0.17
     latter
    0.16
    äºĮèĢħ
    0.15
    两èĢħçļĦ
    0.14
    ä¸īèĢħ
    0.13
    åħ©èĢħ
    0.12
     keduanya
    0.11
     Keduanya
    0.10
    Activations Density 0.175%

    No Known Activations