© 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. 15061
    Prev
    Next
    INDEX
    Explanations

    college classifications

    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
    ,proto
    -0.08
    yster
    -0.08
    forder
    -0.08
    %%%%
    -0.08
    yor
    -0.07
    ouw
    -0.07
    oba
    -0.07
    Įĵ
    -0.07
    aaS
    -0.07
    apol
    -0.07
    POSITIVE LOGITS
    æķ¬è¯·åħ³æ³¨
    0.07
    alan
    0.07
    dom
    0.07
    èĺĭ
    0.06
    ç»Ħè£ħ
    0.06
     DOM
    0.06
    åŃŁ
    0.06
    çª
    0.06
    åĨ³
    0.06
    åĮ¹åħĭ
    0.06
    Activations Density 0.001%

    No Known Activations