© 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. 8545
    Prev
    Next
    INDEX
    Explanations

    URL encoding

    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
    Ø°
    -0.07
    度çļĦ
    -0.07
    ibo
    -0.07
    jev
    -0.06
    ìĤ´
    -0.06
    å®ļæĢ§
    -0.06
    obo
    -0.06
    Ĵáŀ
    -0.06
    æ±Ĥ
    -0.06
    ibi
    -0.06
    POSITIVE LOGITS
    RESET
    0.08
    è¿Ļè¾¹çļĦ
    0.07
    ATEN
    0.07
    ãĢģãĢģãĢģ
    0.07
    ãĢģãĢģ
    0.07
    第ä¹Ŀå±Ĭ
    0.07
    bote
    0.07
    åŁ
    0.07
    åħ«éĥ¨
    0.07
    .dirty
    0.07
    Activations Density 0.008%

    No Known Activations