© 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. 56569
    Prev
    Next
    INDEX
    Explanations

    and etc

    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
    nok
    -0.09
    umon
    -0.08
    DRV
    -0.07
    ANDARD
    -0.07
    verd
    -0.07
    è°ĥæŁ¥éĹ®åį·
    -0.07
    é¢Ĩ导åıĬ
    -0.07
     succesfully
    -0.07
    ivel
    -0.07
    çļĦçĶŁ
    -0.07
    POSITIVE LOGITS
     etc
    0.12
    çŃīçŃī
    0.10
    etc
    0.10
    letz
    0.07
    çŃīè¿Ľè¡Į
    0.07
    设å¤ĩçŃī
    0.07
     finally
    0.07
     blah
    0.07
     usw
    0.07
    —all
    0.07
    Activations Density 0.136%

    No Known Activations