© 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. 10221
    Prev
    Next
    INDEX
    Explanations

    the [adj]

    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
    ment
    -0.10
    ness
    -0.10
    maa
    -0.08
    itude
    -0.08
    ation
    -0.08
    Ø©
    -0.07
    ä¼¼çļĦ
    -0.07
     sucedido
    -0.07
    agak
    -0.07
    çĦī
    -0.07
    POSITIVE LOGITS
    oretical
    0.10
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.09
    .k
    0.09
    oret
    0.08
     only
    0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.08
     cornerstone
    0.08
    ffect
    0.08
    KA
    0.08
    ories
    0.07
    Activations Density 0.107%

    No Known Activations