© 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. 9026
    Prev
    Next
    INDEX
    Explanations

    Swift class variable declaration

    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
    ^
    -0.07
    athon
    -0.06
    LESS
    -0.06
    ä¸Ģè¯į
    -0.06
    \
    -0.06
    ÙĪÙģ
    -0.06
    èĩ³æŀģ
    -0.06
    apura
    -0.06
    arie
    -0.06
    èĬĤèĬĤ
    -0.06
    POSITIVE LOGITS
    aeda
    0.08
    tn
    0.08
    ï¸İ
    0.08
    hea
    0.08
    å°Ķçī¹
    0.08
    å°Ķ夫
    0.08
    çIJ¦
    0.08
    ä½°
    0.08
    çĦ¶å¤§
    0.08
    esus
    0.08
    Activations Density 0.418%

    No Known Activations