© 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. 50090
    Prev
    Next
    INDEX
    Explanations

    code blocks or commands

    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
    hood
    -0.10
    thern
    -0.09
    ermal
    -0.09
    levard
    -0.09
    hape
    -0.09
    ยà¸Ļà¸ķรà¹Į
    -0.09
    äºĨ对
    -0.09
    psilon
    -0.08
    JECT
    -0.08
    à¦ģ
    -0.08
    POSITIVE LOGITS
    Ùĩ
    0.14
    ãĥ³
    0.14
    ers
    0.11
    i
    0.10
    es
    0.10
    ment
    0.10
    ÙĩÙī
    0.09
    ÙĬØ©
    0.09
    ed
    0.09
    as
    0.09
    Activations Density 0.022%

    No Known Activations