© 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. 12484
    Prev
    Next
    INDEX
    Explanations

    HTML tags or technical terms

    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
    ÎŃÏģγ
    -0.08
    çĶ¨çģ«
    -0.08
    ikel
    -0.08
    ä¸Ńæĸĩç½ij
    -0.08
    éļıå¤Ħ
    -0.08
    åĨįä»İ
    -0.08
    artz
    -0.08
    -bars
    -0.07
    é¼ł
    -0.07
    묻
    -0.07
    POSITIVE LOGITS
    çIJ¦
    0.06
    l
    0.06
    lai
    0.06
     Santos
    0.06
    lice
    0.06
     acquiring
    0.06
    ħ
    0.06
    ekyll
    0.06
    st
    0.06
    kken
    0.05
    Activations Density 0.001%

    No Known Activations