© 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. 46094
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    æĪijè¦ģè¯Ħ论
    -0.07
    rel
    -0.07
    ippy
    -0.07
     rao
    -0.07
    çŁ
    -0.07
    eman
    -0.06
    ï¼Ĭï¼Ĭ
    -0.06
    .prototype
    -0.06
    да
    -0.06
    LayoutParams
    -0.06
    POSITIVE LOGITS
    é£Ł
    0.07
    Ñħол
    0.07
    oloc
    0.07
    ién
    0.07
    боÑĢо
    0.06
    ignes
    0.06
    aled
    0.06
    èĬ³èįī
    0.06
    ignano
    0.06
    ä¸ĭåŃ¦æľŁ
    0.06
    Activations Density 0.123%

    No Known Activations