© 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. 9115
    Prev
    Next
    INDEX
    Explanations

    off-target effects or violation

    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
     háºŃu
    -0.08
    åīįéĢĶ
    -0.08
    opa
    -0.07
    .gov
    -0.07
    åIJİ端
    -0.07
    åIJİçĽ¾
    -0.07
    asu
    -0.07
    ASTE
    -0.07
    èĥĮåIJİçļĦ
    -0.07
    upa
    -0.07
    POSITIVE LOGITS
    ities
    0.08
     BETWEEN
    0.08
     entries
    0.08
    çĶŁè¾ī
    0.08
     zwischen
    0.07
     мÑĸж
    0.07
    ict
    0.07
     ÙĪبÙĬÙĨ
    0.07
    (inter
    0.07
    icts
    0.07
    Activations Density 0.002%

    No Known Activations