© 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. 38314
    Prev
    Next
    INDEX
    Explanations

    listing items or sequences

    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
    pers
    -0.09
    anity
    -0.08
    amanya
    -0.07
    pite
    -0.07
    aec
    -0.07
    aeda
    -0.07
    биÑĢ
    -0.07
    atra
    -0.07
    pia
    -0.07
    icha
    -0.07
    POSITIVE LOGITS
    çŃīçŃī
    0.15
     enfin
    0.13
     наконеÑĨ
    0.12
    è¿ĺæľīå°±æĺ¯
    0.12
    以åıĬ
    0.11
    以åıĬ对
    0.10
     etc
    0.10
     ë§Īì§Ģë§īìľ¼ë¡ľ
    0.10
     Lastly
    0.10
     infine
    0.09
    Activations Density 0.335%

    No Known Activations