© 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. 29186
    Prev
    Next
    INDEX
    Explanations

    sequence completion

    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
    imits
    -0.09
    oc
    -0.07
    istics
    -0.07
    Hub
    -0.06
    æĤł
    -0.06
    leb
    -0.06
    ed
    -0.06
    éļIJ
    -0.06
    端起
    -0.06
     ((!
    -0.06
    POSITIVE LOGITS
    undy
    0.08
    гноз
    0.08
     СвеÑĢ
    0.08
    å¿ĥæĦ¿
    0.07
    arra
    0.07
    mant
    0.07
    åĬ¨èĦij
    0.07
     verf
    0.07
    ваÑĩ
    0.07
    åħįè´¹åĴ¨è¯¢
    0.07
    Activations Density 0.021%

    No Known Activations