© 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. 2546
    Prev
    Next
    INDEX
    Explanations

    lists ending in 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
    aider
    -0.07
    elj
    -0.07
    åĩīäºĨ
    -0.07
    å¹´åĮĸ
    -0.07
    uhnya
    -0.07
    olicit
    -0.07
    ommy
    -0.06
     Спа
    -0.06
    araoh
    -0.06
    åĻľ
    -0.06
    POSITIVE LOGITS
    çŃīçŃī
    0.12
    etc
    0.11
    以åıĬåħ¶ä»ĸ
    0.10
     sonstige
    0.10
    以åıĬåľ¨
    0.09
    although
    0.09
    åħ¶å®ĥ
    0.09
     amongst
    0.09
     etc
    0.09
     usw
    0.09
    Activations Density 1.233%

    No Known Activations