© 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. 9854
    Prev
    Next
    INDEX
    Explanations

    This ambivalence

    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
     “
    -0.09
    ’
    -0.08
     (“
    -0.08
     ‘
    -0.08
    æ¸ħ
    -0.07
    /
    -0.07
    ï¼Ī
    -0.07
     (
    -0.07
    ’s
    -0.07
    âĢ¦
    -0.07
    POSITIVE LOGITS
    建平
    0.10
    ujan
    0.09
    çĢļ
    0.09
    emez
    0.09
    åŁŁç½ij
    0.09
    ieger
    0.09
    ç¿°
    0.09
    éĮ²
    0.09
    andung
    0.09
    envir
    0.09
    Activations Density 0.295%

    No Known Activations