© 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. 2071
    Prev
    Next
    INDEX
    Explanations

    example or illustration

    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
    ampi
    -0.08
    è°ĥçłĶåijĺ
    -0.07
     ube
    -0.07
    bsub
    -0.07
    йм
    -0.07
    ihaz
    -0.07
     SINH
    -0.07
     ÙĤب
    -0.07
    以ä¸Ĭãģ®
    -0.07
    .bio
    -0.07
    POSITIVE LOGITS
    该æ¡Ī
    0.08
    åıĪå¦Ĥ
    0.07
    å¹»
    0.07
    _contract
    0.07
     example
    0.07
    è¯łéĩĬäºĨ
    0.07
     expected
    0.07
     hel
    0.06
    æľĽ
    0.06
    示ä¾ĭ
    0.06
    Activations Density 0.017%

    No Known Activations