© 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. 14490
    Prev
    Next
    INDEX
    Explanations

    year number

    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
     HuffPost
    -0.08
    uma
    -0.08
    TURE
    -0.08
    ]=>
    -0.07
    ompiler
    -0.07
    -bs
    -0.07
     Matchers
    -0.07
    ambut
    -0.07
    åħ¶ä¹IJ
    -0.07
     Casal
    -0.07
    POSITIVE LOGITS
    èµ·èįī
    0.06
    FC
    0.06
    æķ°æį®ç»Łè®¡
    0.06
    duc
    0.06
     Copp
    0.06
    èĵ®
    0.06
    GN
    0.06
     Frag
    0.06
    FD
    0.06
    Fd
    0.06
    Activations Density 1.195%

    No Known Activations