© 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. 27681
    Prev
    Next
    INDEX
    Explanations

    set followed by specific words

    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
    à¸ģารสรà¹īาà¸ĩ
    -0.07
    راÙģ
    -0.07
    å°ıè§Ħ模
    -0.07
    inste
    -0.07
    agh
    -0.07
    inato
    -0.06
    ané
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    ÑģлÑĮ
    -0.06
    ForResult
    -0.06
    POSITIVE LOGITS
    åĴĮè°ĥæķ´
    0.09
    /get
    0.09
    OrUpdate
    0.09
    /update
    0.09
    cion
    0.08
    Äiju
    0.08
     semula
    0.08
    /change
    0.08
    uce
    0.08
    tle
    0.08
    Activations Density 0.052%

    No Known Activations