© 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. 46119
    Prev
    Next
    INDEX
    Explanations

    permeability and affinity

    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
    ially
    -0.08
    bies
    -0.07
    ãĤº
    -0.07
    lund
    -0.07
    åŃIJéĩĮ
    -0.06
    æĪĸå°ij
    -0.06
    ECK
    -0.06
     شدÙĨ
    -0.06
    ç´«èĸĩ
    -0.06
    tern
    -0.06
    POSITIVE LOGITS
    estes
    0.09
    çĻ¾åĢį
    0.08
    ä¸ĭéĻį
    0.08
    awas
    0.08
    ÑĥÑīеÑģÑĤво
    0.08
    ноÑģÑĤ
    0.08
    çĪĨæ£ļ
    0.07
    houd
    0.07
    нÑĸÑģÑĤÑĮ
    0.07
    ĭ
    0.07
    Activations Density 0.074%

    No Known Activations