© 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. 24922
    Prev
    Next
    INDEX
    Explanations

    section separators

    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
    audit
    -0.08
    vand
    -0.08
    rack
    -0.08
    azit
    -0.08
    åĵĪæĭī
    -0.08
    äd
    -0.08
     afore
    -0.08
    éĵħ
    -0.08
     staf
    -0.08
    =edge
    -0.07
    POSITIVE LOGITS
     dim
    0.06
     forc
    0.06
    ä»Ĺ
    0.06
     Kee
    0.06
    çŁ£
    0.06
    0.06
     Berger
    0.05
     lang
    0.05
    äºİä¸ĸ
    0.05
    Ļ
    0.05
    Activations Density 0.004%

    No Known Activations