© 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. 2211
    Prev
    Next
    INDEX
    Explanations

    questions and statements

    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
     Harding
    -0.08
    ielen
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
     aforementioned
    -0.07
     Bakal
    -0.07
    stats
    -0.07
    umps
    -0.07
    æĹ¢å®ļ
    -0.07
    addons
    -0.07
    راØŃ
    -0.07
    POSITIVE LOGITS
    wright
    0.07
    常è¯Ĩ
    0.06
    ernet
    0.06
    idor
    0.06
     overturned
    0.06
    erah
    0.06
    oriously
    0.06
    yk
    0.06
    ä¸įäºĨ
    0.06
    æĪ¶
    0.06
    Activations Density 0.035%

    No Known Activations