© 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. 63047
    Prev
    Next
    INDEX
    Explanations

    subject review

    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
    AtPath
    -0.09
    اع
    -0.08
    çĽĺé¾Ļ
    -0.08
     ancho
    -0.08
    æŁ¥çľĭçŃĶæ¡Ī解æŀIJ
    -0.08
    kerne
    -0.08
     Ler
    -0.07
    淹没
    -0.07
     stron
    -0.07
    cé
    -0.07
    POSITIVE LOGITS
    ire
    0.06
     entnehmen
    0.06
    nt
    0.06
    tre
    0.06
     Pere
    0.05
    æĽ¦
    0.05
    wolf
    0.05
    pecting
    0.05
     tre
    0.05
    æĻļ
    0.05
    Activations Density 0.833%

    No Known Activations