© 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. 10635
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    erenc
    -0.07
    å¾·æĻº
    -0.07
    éĻ·å®³
    -0.07
     sfr
    -0.06
    din
    -0.06
    er
    -0.06
    cker
    -0.06
    大çĻ½
    -0.06
     Siv
    -0.06
     Upper
    -0.06
    POSITIVE LOGITS
    iqu
    0.08
    onnement
    0.08
    žių
    0.08
    æķ¢
    0.07
     unintended
    0.07
    akers
    0.07
    ILING
    0.07
    è°´
    0.07
    aked
    0.07
    ä¸ŀ
    0.07
    Activations Density 0.001%

    No Known Activations