© 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. 46161
    Prev
    Next
    INDEX
    Explanations

    Âł separators

    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
    es
    -0.06
    ih
    -0.06
    åı¯
    -0.06
    irks
    -0.06
    -0.05
    eler
    -0.05
    ä¸Ģ个
    -0.05
    en
    -0.05
    as
    -0.05
    éĥģéĹ·
    -0.05
    POSITIVE LOGITS
    referer
    0.08
    ontre
    0.08
    cratch
    0.08
    æīĢèĥ½åıĬ
    0.08
    ãĥijãĥ¼ãĥĪ
    0.08
    å¹´éĿĴ
    0.08
    åĤĢ
    0.08
    oundation
    0.08
    SingleNode
    0.08
    WithValue
    0.08
    Activations Density 0.057%

    No Known Activations