© 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. 20725
    Prev
    Next
    INDEX
    Explanations

    selectivity for tumor/cancer/microbial cells

    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
    egang
    -0.08
    å®ŀçī©
    -0.07
    خش
    -0.07
    ä¸įå®ļ
    -0.07
    &E
    -0.07
    пон
    -0.07
     ÄijÆ°Æ¡ng
    -0.07
    гÑĥÑĤ
    -0.07
    èįŁ
    -0.07
    å¾·æĻº
    -0.06
    POSITIVE LOGITS
     selectively
    0.12
     discriminate
    0.09
     desired
    0.09
     Desired
    0.09
     undes
    0.09
    select
    0.08
     selective
    0.08
    desired
    0.08
    -select
    0.08
    åį´ä¸į
    0.08
    Activations Density 0.169%

    No Known Activations