© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51862
    Prev
    Next
    INDEX
    Explanations

    functionality / functional

    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
    edException
    -0.08
    rens
    -0.08
    oller
    -0.08
    Containing
    -0.08
    ufer
    -0.08
    idden
    -0.07
    ÒĻ
    -0.07
    รร
    -0.07
     formada
    -0.07
    izen
    -0.07
    POSITIVE LOGITS
    nalité
    0.10
    ality
    0.10
    æĢ§åľ°
    0.10
    alized
    0.09
    主治
    0.09
    alist
    0.09
    ally
    0.09
    fully
    0.08
    ines
    0.08
    nalités
    0.08
    Activations Density 0.061%

    No Known Activations