© 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. 49005
    Prev
    Next
    INDEX
    Explanations

    preparing to run code or file

    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
    oor
    -0.08
    èĮµ
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
    èĤĦ
    -0.07
    Öģ
    -0.06
    EventType
    -0.06
    ä¸įä¹ħçļĦ
    -0.06
    .mk
    -0.06
    éĩijèĬ±
    -0.06
    å½¹
    -0.06
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.09
    æľī没æľī
    0.08
    ìĿ¸ëį°
    0.08
     hoping
    0.08
     möglichst
    0.08
    "":
    0.07
     íķĺëĬĶëį°
    0.07
     padahal
    0.07
    ä¼ļåıĺå¾Ĺ
    0.07
     {}:
    0.07
    Activations Density 0.003%

    No Known Activations