© 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. 25364
    Prev
    Next
    INDEX
    Explanations

    adjacent groups or proximity

    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
     patron
    -0.07
    å®ĩå®ĻçļĦ
    -0.07
     plen
    -0.07
     patente
    -0.07
    å®°
    -0.07
    uld
    -0.07
    忧å¿ĥ
    -0.06
    erings
    -0.06
    étr
    -0.06
    ä¸Ģå¼ı
    -0.06
    POSITIVE LOGITS
     proximity
    0.09
    æĭĶåĩº
    0.09
     Nähe
    0.07
     stabil
    0.07
    æľīçī¹æ®Ĭ
    0.07
    ema
    0.07
     adjacent
    0.07
     nearby
    0.07
    vic
    0.07
    åĤį
    0.07
    Activations Density 0.004%

    No Known Activations