© 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. 45541
    Prev
    Next
    INDEX
    Explanations

    technical terms or specific topics

    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
    mann
    -0.07
    (?)
    -0.07
    -ish
    -0.06
    fest
    -0.06
    abler
    -0.06
    ed
    -0.06
    feit
    -0.06
    æŀľçĦ¶
    -0.06
    vp
    -0.06
    +]
    -0.06
    POSITIVE LOGITS
    živ
    0.08
    erschap
    0.08
    æľĢè¿ijæĽ´æĸ°
    0.08
    eningen
    0.08
    eyond
    0.07
    folk
    0.07
    razil
    0.07
    å¾·åįİ
    0.07
    à®Ļà¯įà®ķ
    0.07
    à¹ģละà¸ģาร
    0.07
    Activations Density 0.024%

    No Known Activations