© 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. 45632
    Prev
    Next
    INDEX
    Explanations

    original

    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
     privilegi
    -0.07
     splet
    -0.06
    iere
    -0.06
    æŀģ
    -0.06
    ç¡®
    -0.06
    è£Ĥ
    -0.06
    ember
    -0.06
    yen
    -0.06
     Grie
    -0.06
    porti
    -0.06
    POSITIVE LOGITS
     original
    0.12
    åīįèĢħ
    0.10
    åİŁçīĪ
    0.10
    åİŁæĿ¥çļĦ
    0.10
    original
    0.10
     Original
    0.09
    Original
    0.09
     اÙĦأصÙĦÙĬ
    0.09
     originals
    0.09
    åİŁå§ĭçļĦ
    0.09
    Activations Density 0.289%

    No Known Activations