© 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. 50871
    Prev
    Next
    INDEX
    Explanations

    describes or refers to preceding text

    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
    x
    -0.07
    æľ¬é¢ĺçŃĶæ¡Ī
    -0.06
    éļIJèĹı
    -0.06
    æIJŃ
    -0.06
    jen
    -0.06
     tweaking
    -0.06
    p
    -0.06
    shelf
    -0.06
    ä¾Ľç¨¿
    -0.06
    æĢ»éĥ¨
    -0.06
    POSITIVE LOGITS
     panne
    0.08
    ulls
    0.08
    å°Ĩå°±
    0.08
    lien
    0.08
    ç¡·
    0.08
    ÑĢино
    0.07
    å¤ĩ
    0.07
    صرة
    0.07
    packageName
    0.07
    ilar
    0.07
    Activations Density 0.083%

    No Known Activations