© 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. 26013
    Prev
    Next
    INDEX
    Explanations

    going to do

    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
    presso
    -0.09
    zeci
    -0.09
    uong
    -0.08
    бил
    -0.08
    yks
    -0.08
    inion
    -0.08
    aign
    -0.08
    Äħż
    -0.08
    mons
    -0.08
    ggia
    -0.08
    POSITIVE LOGITS
     be
    0.07
    ized
    0.06
    æľīçĶŁ
    0.06
    osit
    0.06
    åºĬä¸Ĭ
    0.06
     probably
    0.06
    roy
    0.06
    æľī
    0.05
    åѦåĬĽ
    0.05
     likely
    0.05
    Activations Density 0.068%

    No Known Activations