© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11757
    Prev
    Next
    INDEX
    Explanations

    math symbols and greek letters

    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
    etton
    -0.08
    ÑģÑĤв
    -0.08
    addAll
    -0.07
    Defaults
    -0.07
     PROFESS
    -0.07
    /general
    -0.07
    çĤ¹è¿ĻéĩĮ
    -0.07
     prata
    -0.07
     Puglia
    -0.07
    jax
    -0.07
    POSITIVE LOGITS
    å±ħæĺĵ
    0.08
    imon
    0.08
    å±Ī
    0.07
    æľ¬èº«
    0.06
    ùi
    0.06
    imoni
    0.06
    ampil
    0.06
    æľ¬èº«çļĦ
    0.06
    éŁ³è°ĥ
    0.06
    _mp
    0.06
    Activations Density 0.004%

    No Known Activations